SlideShare a Scribd company logo
Gert-Jan Both, Remy Kusters
CRI Research, Université Paris Descartes, Paris, France
DeepMoD
Model discovery
neural networks
DeepMoD
Model discovery
neural networks
@GJ_Both
@RemyKusters
AI, ML and statistics
Symbolic MLStatistical ML vs.
@sandserif
Main criticisms …
ML provides uninterpretable
solutions
Goal:
Develop tools to discover interpretable models for quantitative
science
Combine the statistical power of neural networks with the
symbolic power of regression
Approach:
Goal:
Combine the statistical power of neural networks with the
symbolic power of regression
Develop tools to discover interpretable models for quantitative
science
<latexit sha1_base64="OuHvrtTUD9r4pBI06iD0mJxKAcs=">AAACGnicbVDLSgMxFM34rPVVdekmWIQWyjAjgm6EoiAuFWwrtMOQSTNtMPMguZGWYb7Djb/ixoUi7sSNf2NaZ6HWA8k9nHMvyT1BKrgCx/m05uYXFpeWSyvl1bX1jc3K1nZbJVpS1qKJSORNQBQTPGYt4CDYTSoZiQLBOsHt2cTv3DGpeBJfwzhlXkQGMQ85JWAkv+JqH2qjBtTxCc56lIjsPM9xTTew9kfmKoqfjUZ5A9u2XfcrVcd2psCzxC1IFRW49CvvvX5CdcRioIIo1XWdFLyMSOBUsLzc04qlhN6SAesaGpOIKS+brpbjfaP0cZhIc2LAU/XnREYipcZRYDojAkP115uI/3ldDeGxl/E41cBi+v1QqAWGBE9ywn0uGQUxNoRQyc1fMR0SSSiYNMsmBPfvyrOkfWC7hl8dVpunRRwltIv2UA256Ag10QW6RC1E0T16RM/oxXqwnqxX6+27dc4qZnbQL1gfX5Tang4=</latexit>
Differential equation
Space
Time
Noisy Data
Underlying distribution
P(x, t)<latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit><latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit><latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit><latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit>
Approach:
<latexit sha1_base64="OuHvrtTUD9r4pBI06iD0mJxKAcs=">AAACGnicbVDLSgMxFM34rPVVdekmWIQWyjAjgm6EoiAuFWwrtMOQSTNtMPMguZGWYb7Djb/ixoUi7sSNf2NaZ6HWA8k9nHMvyT1BKrgCx/m05uYXFpeWSyvl1bX1jc3K1nZbJVpS1qKJSORNQBQTPGYt4CDYTSoZiQLBOsHt2cTv3DGpeBJfwzhlXkQGMQ85JWAkv+JqH2qjBtTxCc56lIjsPM9xTTew9kfmKoqfjUZ5A9u2XfcrVcd2psCzxC1IFRW49CvvvX5CdcRioIIo1XWdFLyMSOBUsLzc04qlhN6SAesaGpOIKS+brpbjfaP0cZhIc2LAU/XnREYipcZRYDojAkP115uI/3ldDeGxl/E41cBi+v1QqAWGBE9ywn0uGQUxNoRQyc1fMR0SSSiYNMsmBPfvyrOkfWC7hl8dVpunRRwltIv2UA256Ag10QW6RC1E0T16RM/oxXqwnqxX6+27dc4qZnbQL1gfX5Tang4=</latexit>
Analytic solution
Space
Time
<latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit>
Noisy Data
DeepMoD
Model discovery
neural networks
DeepMoD
Model discovery
neural networks
Code available:
github.com/PhIMaL
<latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit>
Dataset Neural Network Thresh
ˆuu
Auto. Diff.
∂t ˆu = Θξ
Library
Include in cost function
NN converged
ξ∗
= ξ ·
||
||
×
×
×
×
× ×
×
×
ξ∗
Update cost f
Space
Time
Burgers equation
∂tu = uux − 0.1uxx
L = MSE(u, ˆu)
+ MSE(∂t ˆu, Θξ)
+ L1(ξ)
= ...
u
ux
uux
u2
uxx
Space
Time
<latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit>
SolutionNoisy Data
DeepMoD
Model discovery
neural networks
DeepMoD
Model discovery
neural networks
Code available:
github.com/PhIMaL
<latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit>
aset Neural Network Threshold
ˆuu
Auto. Diff.
∂t ˆu = Θξ
Library
Include in cost function
NN converged
ξ∗
= ξ ·
||Θ||
||ut||
So
Sparsity converge
×
×
×
×
× ×
×
×
×
×
×
keep
set to
zero
keep
ξ∗
Update cost function
ace
equation
x − 0.1uxx
L = MSE(u, ˆu)
+ MSE(∂t ˆu, Θξ)
+ L1(ξ)
= ...
u
ux
uux
u2
uxx
Fou
∂tu =
Space
Time
<latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit>
⇠⇤
=<latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit>
Neural Network Threshold
ˆuu
Auto. Diff.
∂t ˆu = Θξ
Library
Include in cost function
NN converged
ξ∗
= ξ ·
||Θ||
||ut||
Solution
Sparsity converged
×
×
×
×
× ×
×
×
×
×
×
keep
set to
zero
keep
ξ∗
Update cost function
L = MSE(u, ˆu)
+ MSE(∂t ˆu, Θξ)
+ L1(ξ)
= ...
u
ux
uux
u2
uxx
Found solution
∂tu = uux − 0.1uxx
0
0
1
0
...
-0.1
0
uux
uxx
u
ux
u2
uxx
<latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit>
SolutionNoisy Data Regression
Code available:
github.com/PhIMaL
DeepMoD
Model discovery
neural networks
DeepMoD
Model discovery
neural networks
5% white noise …
Why does it fail with noise?
Θ =
! ! !
u ux uxu
! ! !
! ! !
uxx uxxu uxxux
! ! !
"
⎛
⎝
⎜
⎜
⎜
⎞
⎠
⎟
⎟
⎟
Numerically calculating library impossible …
uxx(x)<latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit><latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit><latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit><latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit>
ux(x)<latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit><latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit><latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit><latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit>
u(x)<latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit><latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit><latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit><latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit>
Our approach …
Input
The Neural Network
(~x, t)<latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit>
ˆu<latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit>
Output
Space
Time
<latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit>
Construct the library w.r.t. the inferred solution
Θ =
! ! !
u ux uxu
! ! !
! ! !
uxx uxxu uxxux
! ! !
"
⎛
⎝
⎜
⎜
⎜
⎞
⎠
⎟
⎟
⎟
^ ^ ^ ^ ^ ^ ^ ^ ^
Include the regression task within the neural network
How do we train a neural network
Optimise loss function:
L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit>
Learn the mapping
(~x, t) ! ~u<latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit>
Approximate the data as good as possible …
How do we train a neural network
Optimise loss function:
L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit>
Learn the mapping
(~x, t) ! ~u<latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit>
Approximate the data as good as possible …
Regression
(Seek the PDE)
Discover the differential equation
L1 Penalty
Promoting sparsity
How do we train a neural network
Optimise loss function:
L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit>
Learn the mapping
(~x, t) ! ~u<latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit>
Approximate the data as good as possible …
Regression
(Seek the PDE)
Discover the differential equation
Convergence
ξ
optimised
MSE
minimized
c)
Training the neural network
c)
<latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit>
⇠⇤
=<latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit>
Neural Network Threshold
ˆuu
Auto. Diff.
∂t ˆu = Θξ
Library
Include in cost function
NN converged
ξ∗
= ξ ·
||Θ||
||ut||
Solution
Sparsity converged
×
×
×
×
× ×
×
×
×
×
×
keep
set to
zero
keep
ξ∗
Update cost function
L = MSE(u, ˆu)
+ MSE(∂t ˆu, Θξ)
+ L1(ξ)
= ...
u
ux
uux
u2
uxx
Found solution
∂tu = uux − 0.1uxx
0
0
1
0
...
-0.1
0
uux
uxx
u
ux
u2
uxx
Convergence
ξ
optimised
MSE
minimized
c)
Training the coefficient vector
<latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit>
Dataset Neural Network Threshold
ˆuu
Auto. Diff.
∂t ˆu = Θξ
Library
Include in cost function
NN converged
ξ∗
= ξ ·
||Θ||
||ut||
Sparsity c
×
×
×
×
× ×
×
×
×
×
×
keep
set to
zero
keep
ξ∗
Update cost function
Space
Time
Burgers equation
∂tu = uux − 0.1uxx
L = MSE(u, ˆu)
+ MSE(∂t ˆu, Θξ)
+ L1(ξ)
= ...
u
ux
uux
u2
uxx
Space
Time
<latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit>
SolutionNoisy Data Regression
Code available:
github.com/PhIMaL
L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit>
Neural network
(~x, t)<latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit>
ˆu<latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit>
⇠⇤
=<latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit>
Neural Network Threshold
ˆuu
Auto. Diff.
∂t ˆu = Θξ
Library
Include in cost function
NN converged
ξ∗
= ξ ·
||Θ||
||ut||
Solution
Sparsity converged
×
×
×
×
× ×
×
×
×
×
×
keep
set to
zero
keep
ξ∗
Update cost function
L = MSE(u, ˆu)
+ MSE(∂t ˆu, Θξ)
+ L1(ξ)
= ...
u
ux
uux
u2
uxx
Found solution
∂tu = uux − 0.1uxx
0
0
1
0
...
-0.1
0
uux
uxx
u
ux
u2
uxx
DeepMoD
Model discovery
neural networks
DeepMoD
Model discovery
neural networks
u
x
<latexit sha1_base64="6yAhDb2lEN8ufJi3rjVOCio5Mf8=">AAACAnicbZDLSgMxFIYz9VbrbdSVuAkWQRDLjAi6EYpuXFawF2iHIZOmbWgmMyQn0jIUN76KGxeKuPUp3Pk2ppeFVn8IfPznHE7OH6WCa/C8Lye3sLi0vJJfLaytb2xuuds7NZ0YRVmVJiJRjYhoJrhkVeAgWCNVjMSRYPWofz2u1++Z0jyRdzBMWRCTruQdTglYK3T3TAj4Ep8YbMIBPsYtOaZsMBiFbtEreRPhv+DPoIhmqoTuZ6udUBMzCVQQrZu+l0KQEQWcCjYqtIxmKaF90mVNi5LETAfZ5IQRPrROG3cSZZ8EPHF/TmQk1noYR7YzJtDT87Wx+V+taaBzEWRcpgaYpNNFHSMwJHicB25zxSiIoQVCFbd/xbRHFKFgUyvYEPz5k/9C7bTkW749K5avZnHk0T46QEfIR+eojG5QBVURRQ/oCb2gV+fReXbenPdpa86ZzeyiX3I+vgEk2JX+</latexit>
Why regression inside neural network?
Resilience to Noise/ sampling size
Relative error on coefficients
<latexit sha1_base64="6yAhDb2lEN8ufJi3rjVOCio5Mf8=">AAACAnicbZDLSgMxFIYz9VbrbdSVuAkWQRDLjAi6EYpuXFawF2iHIZOmbWgmMyQn0jIUN76KGxeKuPUp3Pk2ppeFVn8IfPznHE7OH6WCa/C8Lye3sLi0vJJfLaytb2xuuds7NZ0YRVmVJiJRjYhoJrhkVeAgWCNVjMSRYPWofz2u1++Z0jyRdzBMWRCTruQdTglYK3T3TAj4Ep8YbMIBPsYtOaZsMBiFbtEreRPhv+DPoIhmqoTuZ6udUBMzCVQQrZu+l0KQEQWcCjYqtIxmKaF90mVNi5LETAfZ5IQRPrROG3cSZZ8EPHF/TmQk1noYR7YzJtDT87Wx+V+taaBzEWRcpgaYpNNFHSMwJHicB25zxSiIoQVCFbd/xbRHFKFgUyvYEPz5k/9C7bTkW749K5avZnHk0T46QEfIR+eojG5QBVURRQ/oCb2gV+fReXbenPdpa86ZzeyiX3I+vgEk2JX+</latexit>
Burgers’ equation
Applications in physics
Higher order PDEs
<latexit sha1_base64="89mN2eImzrIm0QzNLSbmbxofcBY=">AAACAHicbZDLSsNAFIYn9VbrLerChZvBIrixJCLqRii6cVnBXqANYTKdtEMnkzAXSQnZ+CpuXCji1sdw59s4bbPQ1gMzfPz/OcycP0gYlcpxvq3S0vLK6lp5vbKxubW9Y+/utWSsBSZNHLNYdAIkCaOcNBVVjHQSQVAUMNIORrcTv/1IhKQxf1DjhHgRGnAaUoyUkXz7QPsKXsMLqKH2U3hq7ixN09y3q07NmRZcBLeAKiiq4dtfvX6MdUS4wgxJ2XWdRHkZEopiRvJKT0uSIDxCA9I1yFFEpJdNF8jhsVH6MIyFOVzBqfp7IkORlOMoMJ0RUkM5703E/7yuVuGVl1GeaEU4nj0UagZVDCdpwD4VBCs2NoCwoOavEA+RQFiZzComBHd+5UVondVcw/fn1fpNEUcZHIIjcAJccAnq4A40QBNgkINn8ArerCfrxXq3PmatJauY2Qd/yvr8Aa06lS4=</latexit>
t = 5
t = 7
t = 9
Ground truth Sampled Inferred
y
y
y
Coupled equations
<latexit sha1_base64="oJZFq0o7Dpv+0FhHmocEH1HfGbM=">AAACJ3icbZDLSgMxFIYzXmu9jbp0EyxCXVhmRNCNUtSFywr2Ap0yZNJMG5rJDMkZtZS+jRtfxY2gIrr0TUzbWWjrgZCP/z+H5PxBIrgGx/my5uYXFpeWcyv51bX1jU17a7um41RRVqWxiFUjIJoJLlkVOAjWSBQjUSBYPehdjvz6HVOax/IW+glrRaQjecgpASP59nnqAz7DniSBIB5tx4A9wUIo4iufZzJO8SH2Hri5M+Eee4p3unDg2wWn5IwLz4KbQQFlVfHtV68d0zRiEqggWjddJ4HWgCjgVLBh3ks1SwjtkQ5rGpQkYro1GO85xPtGaeMwVuZIwGP198SARFr3o8B0RgS6etobif95zRTC09aAyyQFJunkoTAVGGI8Cg23uWIURN8AoYqbv2LaJYpQMNHmTQju9MqzUDsquYZvjgvliyyOHNpFe6iIXHSCyugaVVAVUfSIntEbereerBfrw/qctM5Z2cwO+lPW9w97rKPZ</latexit>
<latexit sha1_base64="TZ48ZV1oiCE1tUaFN922vZ54mwQ=">AAACCXicbZDLSgMxFIYz9VbrrerSzcEiCGKZEUE3QtEuXFawF2iHIZOmbWjmQnLGUkq3bnwVNy4UcesbuPNtTNtZaOuBhI//P4fk/H4shUbb/rYyS8srq2vZ9dzG5tb2Tn53r6ajRDFeZZGMVMOnmksR8ioKlLwRK04DX/K637+Z+PUHrrSIwnscxtwNaDcUHcEoGsnLw8BDuAIoewNolblECgM4hb65T6AHCXj5gl20pwWL4KRQIGlVvPxXqx2xJOAhMkm1bjp2jO6IKhRM8nGulWgeU9anXd40GNKAa3c03WQMR0ZpQydS5oQIU/X3xIgGWg8D33QGFHt63puI/3nNBDuX7kiEcYI8ZLOHOokEjGASC7SF4gzl0ABlSpi/AutRRRma8HImBGd+5UWonRUdw3fnhdJ1GkeWHJBDckwcckFK5JZUSJUw8kieySt5s56sF+vd+pi1Zqx0Zp/8KevzB0yCluA=</latexit>
u<latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit><latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit><latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit><latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit>
w<latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit><latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit><latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit><latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit>
:particle density
:attractant density
2D equations
Raw images Density field
ut = 0.3uy + 0.01uxx + 0.01uyy<latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit><latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit><latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit><latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit>
Underlying AD equation
Apply to real data …
Model discovery from experimental data
Single ParticleTracking
Time
xx
Time
Time
Time
Trajectory
<latexit sha1_base64="A2yY/FcKHQddACwl6l5TaATnAyI=">AAACFXicbZDLSsQwFIZT7463qks3wUEQFGkHQTeC6MalguMMTGtJM+kYTNOSnMgMpS/hxldx40IRt4I738bMZaEz/hD4+M85nJw/zgXX4HnfztT0zOzc/MJiZWl5ZXXNXd+40ZlRlNVpJjLVjIlmgktWBw6CNXPFSBoL1ojvz/v1xgNTmmfyGno5C1PSkTzhlIC1InffRAVAifdwkChCC78sAiAmoiU2EeATHEhzW7NcdLtl5Fa9A28gPAn+CKpopMvI/QraGTUpk0AF0brlezmEBVHAqWBlJTCa5YTekw5rWZQkZTosBleVeMc6bZxkyj4JeOD+nihIqnUvjW1nSuBOj9f65n+1loHkOCy4zA0wSYeLEiMwZLgfEW5zxSiIngVCFbd/xfSO2HTABlmxIfjjJ0/CTe3At3x1WD09G8WxgLbQNtpFPjpCp+gCXaI6ougRPaNX9OY8OS/Ou/MxbJ1yRjOb6I+czx/MZJ6T</latexit>
<latexit sha1_base64="l3iwXAx+BJVV3L+FIIt6mI0zRgc=">AAACAnicbZDLSsNAFIYn9VbrLepK3AwWQRBKIoJuhKIuXFawF2hDmEym7dDJJMyltITgxldx40IRtz6FO9/GaZuFtv4w8PGfczhz/iBhVCrH+bYKS8srq2vF9dLG5tb2jr2715CxFpjUccxi0QqQJIxyUldUMdJKBEFRwEgzGNxM6s0hEZLG/EGNE+JFqMdpl2KkjOXbB9pPVQav4C00NBpl8BQO/RBq6Ntlp+JMBRfBzaEMctV8+6sTxlhHhCvMkJRt10mUlyKhKGYkK3W0JAnCA9QjbYMcRUR66fSEDB4bJ4TdWJjHFZy6vydSFEk5jgLTGSHVl/O1iflfra1V99JLKU+0IhzPFnU1gyqGkzxgSAXBio0NICyo+SvEfSQQVia1kgnBnT95ERpnFdfw/Xm5ep3HUQSH4AicABdcgCq4AzVQBxg8gmfwCt6sJ+vFerc+Zq0FK5/ZB39kff4A+62V2w==</latexit>
<latexit sha1_base64="q8SSRp0DvPa9XRci5Cdg/mAJUPE=">AAAB+nicbZDLSsNAFIZP6q3WW6pLN4NFcFUSEXQjFHXhsoK9QBvCZDpth04mYWaiLTGP4saFIm59Ene+jdM2C239YeDjP+dwzvxBzJnSjvNtFVZW19Y3ipulre2d3T27vN9UUSIJbZCIR7IdYEU5E7Shmea0HUuKw4DTVjC6ntZbD1QqFol7PYmpF+KBYH1GsDaWb5cTP9UZukQ3yNB4nCHfrjhVZya0DG4OFchV9+2vbi8iSUiFJhwr1XGdWHsplpoRTrNSN1E0xmSEB7RjUOCQKi+dnZ6hY+P0UD+S5gmNZu7viRSHSk3CwHSGWA/VYm1q/lfrJLp/4aVMxImmgswX9ROOdISmOaAek5RoPjGAiWTmVkSGWGKiTVolE4K7+OVlaJ5WXcN3Z5XaVR5HEQ7hCE7AhXOowS3UoQEEHuEZXuHNerJerHfrY95asPKZA/gj6/MHPD2TUg==</latexit>
Random walk
Advected random walk
Persistant random walk
x
Density
estimation
Model
discovery
Time
xx
Time
Time
Time
Trajectory
<latexit sha1_base64="A2yY/FcKHQddACwl6l5TaATnAyI=">AAACFXicbZDLSsQwFIZT7463qks3wUEQFGkHQTeC6MalguMMTGtJM+kYTNOSnMgMpS/hxldx40IRt4I738bMZaEz/hD4+M85nJw/zgXX4HnfztT0zOzc/MJiZWl5ZXXNXd+40ZlRlNVpJjLVjIlmgktWBw6CNXPFSBoL1ojvz/v1xgNTmmfyGno5C1PSkTzhlIC1InffRAVAifdwkChCC78sAiAmoiU2EeATHEhzW7NcdLtl5Fa9A28gPAn+CKpopMvI/QraGTUpk0AF0brlezmEBVHAqWBlJTCa5YTekw5rWZQkZTosBleVeMc6bZxkyj4JeOD+nihIqnUvjW1nSuBOj9f65n+1loHkOCy4zA0wSYeLEiMwZLgfEW5zxSiIngVCFbd/xfSO2HTABlmxIfjjJ0/CTe3At3x1WD09G8WxgLbQNtpFPjpCp+gCXaI6ougRPaNX9OY8OS/Ou/MxbJ1yRjOb6I+czx/MZJ6T</latexit>
<latexit sha1_base64="l3iwXAx+BJVV3L+FIIt6mI0zRgc=">AAACAnicbZDLSsNAFIYn9VbrLepK3AwWQRBKIoJuhKIuXFawF2hDmEym7dDJJMyltITgxldx40IRtz6FO9/GaZuFtv4w8PGfczhz/iBhVCrH+bYKS8srq2vF9dLG5tb2jr2715CxFpjUccxi0QqQJIxyUldUMdJKBEFRwEgzGNxM6s0hEZLG/EGNE+JFqMdpl2KkjOXbB9pPVQav4C00NBpl8BQO/RBq6Ntlp+JMBRfBzaEMctV8+6sTxlhHhCvMkJRt10mUlyKhKGYkK3W0JAnCA9QjbYMcRUR66fSEDB4bJ4TdWJjHFZy6vydSFEk5jgLTGSHVl/O1iflfra1V99JLKU+0IhzPFnU1gyqGkzxgSAXBio0NICyo+SvEfSQQVia1kgnBnT95ERpnFdfw/Xm5ep3HUQSH4AicABdcgCq4AzVQBxg8gmfwCt6sJ+vFerc+Zq0FK5/ZB39kff4A+62V2w==</latexit>
<latexit sha1_base64="q8SSRp0DvPa9XRci5Cdg/mAJUPE=">AAAB+nicbZDLSsNAFIZP6q3WW6pLN4NFcFUSEXQjFHXhsoK9QBvCZDpth04mYWaiLTGP4saFIm59Ene+jdM2C239YeDjP+dwzvxBzJnSjvNtFVZW19Y3ipulre2d3T27vN9UUSIJbZCIR7IdYEU5E7Shmea0HUuKw4DTVjC6ntZbD1QqFol7PYmpF+KBYH1GsDaWb5cTP9UZukQ3yNB4nCHfrjhVZya0DG4OFchV9+2vbi8iSUiFJhwr1XGdWHsplpoRTrNSN1E0xmSEB7RjUOCQKi+dnZ6hY+P0UD+S5gmNZu7viRSHSk3CwHSGWA/VYm1q/lfrJLp/4aVMxImmgswX9ROOdISmOaAek5RoPjGAiWTmVkSGWGKiTVolE4K7+OVlaJ5WXcN3Z5XaVR5HEQ7hCE7AhXOowS3UoQEEHuEZXuHNerJerHfrY95asPKZA/gj6/MHPD2TUg==</latexit>
Random walk
Advected random walk
Persistant random walk
x
Density
estimation
Model
discovery
Single ParticleTracking
Density estimation:Temporal normalizing flows
t
z
t
x
Latent spaceReal space
x
t
Positional data
Temporal Normalizing Flows (tNFs) extend NFs with a temporal
component to estimate a time-dependent density evolution
Code available on Github:
https://github.com/PhIMaL
Paper available on arXiv:
1912.09092
Density estimation:Temporal normalizing flows
t
z
t
x
Latent spaceReal space
x
t
Positional data
Temporal Normalizing Flows (tNFs) extend NFs with a temporal
component to estimate a time-dependent density evolution
tNFs allow discovery of PDEs with conservation
constraints, e.g. Fokker-Planck, …
Code available on Github:
https://github.com/PhIMaL
Paper available on arXiv:
1912.09092
Code available on Github:
https://github.com/PhIMaL
DeepMoD
Model discovery
neural networks
DeepMoD
Model discovery
neural networks
Paper available on arXiv:
1904.08406
T. Chrysostomou
(Intern)
C. Le Scao
( Intern)
A, Brandon-Bravo
( Engineer)
G.-J. Both
( PhD)
@GJ_Both
@RemyKusters
Postdoc position available !

More Related Content

Similar to DeepMoD: Deep Learning Model discovery

The current state of prediction in neuroimaging
The current state of prediction in neuroimagingThe current state of prediction in neuroimaging
The current state of prediction in neuroimaging
SaigeRutherford
 
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET Journal
 
AI - history and recent breakthroughs
AI - history and recent breakthroughs AI - history and recent breakthroughs
AI - history and recent breakthroughs
Armando Vieira
 
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Sri Ambati
 
Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"
Aalto University
 
A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...
A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...
A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...
Editor IJCATR
 
AI Market Size, Strategy
AI Market Size, StrategyAI Market Size, Strategy
AI Market Size, Strategy
Purpose+
 
Train, explain, acclaim. Build a good model in three steps
Train, explain, acclaim.  Build a good model in three stepsTrain, explain, acclaim.  Build a good model in three steps
Train, explain, acclaim. Build a good model in three steps
Przemek Biecek
 
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
Wael Alawsey
 
Yuri van Geest, Exponential Organizations - DMX Dublin 2016
Yuri van Geest,  Exponential Organizations - DMX Dublin 2016Yuri van Geest,  Exponential Organizations - DMX Dublin 2016
Yuri van Geest, Exponential Organizations - DMX Dublin 2016
DMX Dublin
 
Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...
Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...
Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...
Amit Sheth
 
FAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable PredictionsFAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable Predictions
Michel Dumontier
 
M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...
M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...
M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...
Marco Brambilla
 
Ai in finance
Ai in financeAi in finance
Ai in finance
QuantUniversity
 
ODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AIODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AI
Aditya Bhattacharya
 
The Science of Data Science
The Science of Data Science The Science of Data Science
The Science of Data Science
James Hendler
 
Machine learning
Machine learningMachine learning
Machine learning
Tushar Nikam
 
Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...
BaoTramDuong2
 
CompetitiveIntelligenceNetworks
CompetitiveIntelligenceNetworksCompetitiveIntelligenceNetworks
CompetitiveIntelligenceNetworks
Eva Ortoll
 
Machine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxMachine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptx
VenkateswaraBabuRavi
 

Similar to DeepMoD: Deep Learning Model discovery (20)

The current state of prediction in neuroimaging
The current state of prediction in neuroimagingThe current state of prediction in neuroimaging
The current state of prediction in neuroimaging
 
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...IRJET-  	  Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
IRJET- Improved Model for Big Data Analytics using Dynamic Multi-Swarm Op...
 
AI - history and recent breakthroughs
AI - history and recent breakthroughs AI - history and recent breakthroughs
AI - history and recent breakthroughs
 
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
Get hands-on with Explainable AI at Machine Learning Interpretability(MLI) Gym!
 
Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"Inverse Modeling for Cognitive Science "in the Wild"
Inverse Modeling for Cognitive Science "in the Wild"
 
A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...
A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...
A Comparative Study of Various Data Mining Techniques: Statistics, Decision T...
 
AI Market Size, Strategy
AI Market Size, StrategyAI Market Size, Strategy
AI Market Size, Strategy
 
Train, explain, acclaim. Build a good model in three steps
Train, explain, acclaim.  Build a good model in three stepsTrain, explain, acclaim.  Build a good model in three steps
Train, explain, acclaim. Build a good model in three steps
 
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
ARTIFICIAL INTELLIGENT ( ITS / TASK 6 ) done by Wael Saad Hameedi / P71062
 
Yuri van Geest, Exponential Organizations - DMX Dublin 2016
Yuri van Geest,  Exponential Organizations - DMX Dublin 2016Yuri van Geest,  Exponential Organizations - DMX Dublin 2016
Yuri van Geest, Exponential Organizations - DMX Dublin 2016
 
Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...
Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...
Semantic, Cognitive, and Perceptual Computing – three intertwined strands of ...
 
FAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable PredictionsFAIR & AI Ready KGs for Explainable Predictions
FAIR & AI Ready KGs for Explainable Predictions
 
M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...
M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...
M.Sc. Thesis Topics and Proposals @ Polimi Data Science Lab - 2024 - prof. Br...
 
Ai in finance
Ai in financeAi in finance
Ai in finance
 
ODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AIODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AI
 
The Science of Data Science
The Science of Data Science The Science of Data Science
The Science of Data Science
 
Machine learning
Machine learningMachine learning
Machine learning
 
Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...Discover How Scientific Data is Used for the Public Good with Natural Languag...
Discover How Scientific Data is Used for the Public Good with Natural Languag...
 
CompetitiveIntelligenceNetworks
CompetitiveIntelligenceNetworksCompetitiveIntelligenceNetworks
CompetitiveIntelligenceNetworks
 
Machine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptxMachine learning ppt unit one syllabuspptx
Machine learning ppt unit one syllabuspptx
 

Recently uploaded

aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
İsa Badur
 
Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.
Nistarini College, Purulia (W.B) India
 
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
David Osipyan
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
Gokturk Mehmet Dilci
 
Applied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdfApplied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdf
University of Hertfordshire
 
Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.
Aditi Bajpai
 
Cytokines and their role in immune regulation.pptx
Cytokines and their role in immune regulation.pptxCytokines and their role in immune regulation.pptx
Cytokines and their role in immune regulation.pptx
Hitesh Sikarwar
 
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
TinyAnderson
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
Daniel Tubbenhauer
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
HongcNguyn6
 
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
University of Maribor
 
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Ana Luísa Pinho
 
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
yqqaatn0
 
Nucleophilic Addition of carbonyl compounds.pptx
Nucleophilic Addition of carbonyl  compounds.pptxNucleophilic Addition of carbonyl  compounds.pptx
Nucleophilic Addition of carbonyl compounds.pptx
SSR02
 
Chapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisisChapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisis
tonzsalvador2222
 
8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf
by6843629
 
bordetella pertussis.................................ppt
bordetella pertussis.................................pptbordetella pertussis.................................ppt
bordetella pertussis.................................ppt
kejapriya1
 
Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...
Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...
Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...
Travis Hills MN
 
The binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defectsThe binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defects
Sérgio Sacani
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
KrushnaDarade1
 

Recently uploaded (20)

aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
 
Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.
 
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
 
Applied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdfApplied Science: Thermodynamics, Laws & Methodology.pdf
Applied Science: Thermodynamics, Laws & Methodology.pdf
 
Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.
 
Cytokines and their role in immune regulation.pptx
Cytokines and their role in immune regulation.pptxCytokines and their role in immune regulation.pptx
Cytokines and their role in immune regulation.pptx
 
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdfTopic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
Topic: SICKLE CELL DISEASE IN CHILDREN-3.pdf
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
 
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốtmô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
mô tả các thí nghiệm về đánh giá tác động dòng khí hóa sau đốt
 
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
 
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
 
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
 
Nucleophilic Addition of carbonyl compounds.pptx
Nucleophilic Addition of carbonyl  compounds.pptxNucleophilic Addition of carbonyl  compounds.pptx
Nucleophilic Addition of carbonyl compounds.pptx
 
Chapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisisChapter 12 - climate change and the energy crisis
Chapter 12 - climate change and the energy crisis
 
8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf8.Isolation of pure cultures and preservation of cultures.pdf
8.Isolation of pure cultures and preservation of cultures.pdf
 
bordetella pertussis.................................ppt
bordetella pertussis.................................pptbordetella pertussis.................................ppt
bordetella pertussis.................................ppt
 
Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...
Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...
Travis Hills' Endeavors in Minnesota: Fostering Environmental and Economic Pr...
 
The binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defectsThe binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defects
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
 

DeepMoD: Deep Learning Model discovery

  • 1. Gert-Jan Both, Remy Kusters CRI Research, Université Paris Descartes, Paris, France DeepMoD Model discovery neural networks DeepMoD Model discovery neural networks @GJ_Both @RemyKusters
  • 2. AI, ML and statistics Symbolic MLStatistical ML vs. @sandserif Main criticisms … ML provides uninterpretable solutions
  • 3. Goal: Develop tools to discover interpretable models for quantitative science Combine the statistical power of neural networks with the symbolic power of regression Approach:
  • 4. Goal: Combine the statistical power of neural networks with the symbolic power of regression Develop tools to discover interpretable models for quantitative science <latexit sha1_base64="OuHvrtTUD9r4pBI06iD0mJxKAcs=">AAACGnicbVDLSgMxFM34rPVVdekmWIQWyjAjgm6EoiAuFWwrtMOQSTNtMPMguZGWYb7Djb/ixoUi7sSNf2NaZ6HWA8k9nHMvyT1BKrgCx/m05uYXFpeWSyvl1bX1jc3K1nZbJVpS1qKJSORNQBQTPGYt4CDYTSoZiQLBOsHt2cTv3DGpeBJfwzhlXkQGMQ85JWAkv+JqH2qjBtTxCc56lIjsPM9xTTew9kfmKoqfjUZ5A9u2XfcrVcd2psCzxC1IFRW49CvvvX5CdcRioIIo1XWdFLyMSOBUsLzc04qlhN6SAesaGpOIKS+brpbjfaP0cZhIc2LAU/XnREYipcZRYDojAkP115uI/3ldDeGxl/E41cBi+v1QqAWGBE9ywn0uGQUxNoRQyc1fMR0SSSiYNMsmBPfvyrOkfWC7hl8dVpunRRwltIv2UA256Ag10QW6RC1E0T16RM/oxXqwnqxX6+27dc4qZnbQL1gfX5Tang4=</latexit> Differential equation Space Time Noisy Data Underlying distribution P(x, t)<latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit><latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit><latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit><latexit sha1_base64="3XtpKznpBSb+nMyPAQPZfV01TDk=">AAAB7XicbZBNSwMxEIZn61etX1WPXhaLUEHKrgh6LHrxWMF+QLuUbJq2sdlkSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZecNYcIOe9+3kVlbX1jfym4Wt7Z3dveL+QcOoRFNWp0oo3QqJYYJLVkeOgrVizUgUCtYMRzfTevORacOVvMdxzIKIDCTvc0rQWo1a+ekMT7vFklfxZnKXwc+gBJlq3eJXp6doEjGJVBBj2r4XY5ASjZwKNil0EsNiQkdkwNoWJYmYCdLZthP3xDo9t6+0fRLdmft7IiWRMeMotJ0RwaFZrE3N/2rtBPtXQcplnCCTdP5RPxEuKnd6utvjmlEUYwuEam53demQaELRBlSwIfiLJy9D47ziW767KFWvszjycATHUAYfLqEKt1CDOlB4gGd4hTdHOS/Ou/Mxb8052cwh/JHz+QOJ2I5v</latexit> Approach:
  • 5. <latexit sha1_base64="OuHvrtTUD9r4pBI06iD0mJxKAcs=">AAACGnicbVDLSgMxFM34rPVVdekmWIQWyjAjgm6EoiAuFWwrtMOQSTNtMPMguZGWYb7Djb/ixoUi7sSNf2NaZ6HWA8k9nHMvyT1BKrgCx/m05uYXFpeWSyvl1bX1jc3K1nZbJVpS1qKJSORNQBQTPGYt4CDYTSoZiQLBOsHt2cTv3DGpeBJfwzhlXkQGMQ85JWAkv+JqH2qjBtTxCc56lIjsPM9xTTew9kfmKoqfjUZ5A9u2XfcrVcd2psCzxC1IFRW49CvvvX5CdcRioIIo1XWdFLyMSOBUsLzc04qlhN6SAesaGpOIKS+brpbjfaP0cZhIc2LAU/XnREYipcZRYDojAkP115uI/3ldDeGxl/E41cBi+v1QqAWGBE9ywn0uGQUxNoRQyc1fMR0SSSiYNMsmBPfvyrOkfWC7hl8dVpunRRwltIv2UA256Ag10QW6RC1E0T16RM/oxXqwnqxX6+27dc4qZnbQL1gfX5Tang4=</latexit> Analytic solution Space Time <latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit> Noisy Data DeepMoD Model discovery neural networks DeepMoD Model discovery neural networks Code available: github.com/PhIMaL
  • 6. <latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit> Dataset Neural Network Thresh ˆuu Auto. Diff. ∂t ˆu = Θξ Library Include in cost function NN converged ξ∗ = ξ · || || × × × × × × × × ξ∗ Update cost f Space Time Burgers equation ∂tu = uux − 0.1uxx L = MSE(u, ˆu) + MSE(∂t ˆu, Θξ) + L1(ξ) = ... u ux uux u2 uxx Space Time <latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit> SolutionNoisy Data DeepMoD Model discovery neural networks DeepMoD Model discovery neural networks Code available: github.com/PhIMaL
  • 7. <latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit> aset Neural Network Threshold ˆuu Auto. Diff. ∂t ˆu = Θξ Library Include in cost function NN converged ξ∗ = ξ · ||Θ|| ||ut|| So Sparsity converge × × × × × × × × × × × keep set to zero keep ξ∗ Update cost function ace equation x − 0.1uxx L = MSE(u, ˆu) + MSE(∂t ˆu, Θξ) + L1(ξ) = ... u ux uux u2 uxx Fou ∂tu = Space Time <latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit> ⇠⇤ =<latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit> Neural Network Threshold ˆuu Auto. Diff. ∂t ˆu = Θξ Library Include in cost function NN converged ξ∗ = ξ · ||Θ|| ||ut|| Solution Sparsity converged × × × × × × × × × × × keep set to zero keep ξ∗ Update cost function L = MSE(u, ˆu) + MSE(∂t ˆu, Θξ) + L1(ξ) = ... u ux uux u2 uxx Found solution ∂tu = uux − 0.1uxx 0 0 1 0 ... -0.1 0 uux uxx u ux u2 uxx <latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit> SolutionNoisy Data Regression Code available: github.com/PhIMaL DeepMoD Model discovery neural networks DeepMoD Model discovery neural networks
  • 8. 5% white noise … Why does it fail with noise? Θ = ! ! ! u ux uxu ! ! ! ! ! ! uxx uxxu uxxux ! ! ! " ⎛ ⎝ ⎜ ⎜ ⎜ ⎞ ⎠ ⎟ ⎟ ⎟ Numerically calculating library impossible … uxx(x)<latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit><latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit><latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit><latexit sha1_base64="QNA18qBfAJrCCEwMxK/B/I1M350=">AAAB8HicbZDLSgMxFIbP1Futt6pLN8Ei1E2ZEUGXRTcuK9iLtEPJpJk2NMkMSUZahj6FGxeKuPVx3Pk2ZtpZaOsPgY//nEPO+YOYM21c99sprK1vbG4Vt0s7u3v7B+XDo5aOEkVok0Q8Up0Aa8qZpE3DDKedWFEsAk7bwfg2q7efqNIskg9mGlNf4KFkISPYWOsx6aeTyaw6Oe+XK27NnQutgpdDBXI1+uWv3iAiiaDSEI617npubPwUK8MIp7NSL9E0xmSMh7RrUWJBtZ/OF56hM+sMUBgp+6RBc/f3RIqF1lMR2E6BzUgv1zLzv1o3MeG1nzIZJ4ZKsvgoTDgyEcquRwOmKDF8agETxeyuiIywwsTYjEo2BG/55FVoXdQ8y/eXlfpNHkcRTuAUquDBFdThDhrQBAICnuEV3hzlvDjvzseiteDkM8fwR87nD707kFk=</latexit> ux(x)<latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit><latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit><latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit><latexit sha1_base64="tjArAx6NhzxT95XjS0tfOz6ea7o=">AAAB73icbZBNSwMxEIZn61etX1WPXoJFqJeyK4Iei148VrAf0C4lm07b0Gx2TbLSsvRPePGgiFf/jjf/jWm7B219IfDwzgyZeYNYcG1c99vJra1vbG7ltws7u3v7B8XDo4aOEsWwziIRqVZANQousW64EdiKFdIwENgMRrezevMJleaRfDCTGP2QDiTvc0aNtVpJNx1Py+PzbrHkVty5yCp4GZQgU61b/Or0IpaEKA0TVOu258bGT6kynAmcFjqJxpiyER1g26KkIWo/ne87JWfW6ZF+pOyThszd3xMpDbWehIHtDKkZ6uXazPyv1k5M/9pPuYwTg5ItPuongpiIzI4nPa6QGTGxQJnidlfChlRRZmxEBRuCt3zyKjQuKp7l+8tS9SaLIw8ncApl8OAKqnAHNagDAwHP8ApvzqPz4rw7H4vWnJPNHMMfOZ8/3rOP1w==</latexit> u(x)<latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit><latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit><latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit><latexit sha1_base64="xyz5fYmv7DAMjqhOp6NQw7olzvk=">AAAB63icbZDNSgMxFIXv1L9a/6ou3QSLUDdlRgRdFt24rOC0hXYomTTThiaZIcmIZegruHGhiFtfyJ1vY6adhbYeCHycey+594QJZ9q47rdTWlvf2Nwqb1d2dvf2D6qHR20dp4pQn8Q8Vt0Qa8qZpL5hhtNuoigWIaedcHKb1zuPVGkWywczTWgg8EiyiBFsciutP50PqjW34c6FVsEroAaFWoPqV38Yk1RQaQjHWvc8NzFBhpVhhNNZpZ9qmmAywSPasyixoDrI5rvO0Jl1hiiKlX3SoLn7eyLDQuupCG2nwGasl2u5+V+tl5roOsiYTFJDJVl8FKUcmRjlh6MhU5QYPrWAiWJ2V0TGWGFibDwVG4K3fPIqtC8anuX7y1rzpoijDCdwCnXw4AqacAct8IHAGJ7hFd4c4bw4787HorXkFDPH8EfO5w+DSo3g</latexit>
  • 9. Our approach … Input The Neural Network (~x, t)<latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit> ˆu<latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit> Output Space Time <latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit> Construct the library w.r.t. the inferred solution Θ = ! ! ! u ux uxu ! ! ! ! ! ! uxx uxxu uxxux ! ! ! " ⎛ ⎝ ⎜ ⎜ ⎜ ⎞ ⎠ ⎟ ⎟ ⎟ ^ ^ ^ ^ ^ ^ ^ ^ ^ Include the regression task within the neural network
  • 10. How do we train a neural network Optimise loss function: L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit> Learn the mapping (~x, t) ! ~u<latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit> Approximate the data as good as possible …
  • 11. How do we train a neural network Optimise loss function: L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit> Learn the mapping (~x, t) ! ~u<latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit> Approximate the data as good as possible … Regression (Seek the PDE) Discover the differential equation
  • 12. L1 Penalty Promoting sparsity How do we train a neural network Optimise loss function: L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit> Learn the mapping (~x, t) ! ~u<latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit><latexit sha1_base64="yJgnElJriwfv2D53AURbemLgi/I=">AAACCHicbZDLSsNAFIYn9VbrLerShYNFqCAlEUGXRTcuK9gLNKFMptN26OTCzEm1hCzd+CpuXCji1kdw59s4TbPQ1h8GPv5zDmfO70WCK7Csb6OwtLyyulZcL21sbm3vmLt7TRXGkrIGDUUo2x5RTPCANYCDYO1IMuJ7grW80fW03hozqXgY3MEkYq5PBgHvc0pAW13zsOKMGU0e0lM4wY7kgyEQKcN7nNlx2jXLVtXKhBfBzqGMctW75pfTC2nsswCoIEp1bCsCNyESOBUsLTmxYhGhIzJgHY0B8Zlyk+yQFB9rp4f7odQvAJy5vycS4is18T3d6RMYqvna1Pyv1omhf+kmPIhiYAGdLerHAkOIp6ngHpeMgphoIFRy/VdMh0QSCjq7kg7Bnj95EZpnVVvz7Xm5dpXHUUQH6AhVkI0uUA3doDpqIIoe0TN6RW/Gk/FivBsfs9aCkc/soz8yPn8AtuSZyA==</latexit> Approximate the data as good as possible … Regression (Seek the PDE) Discover the differential equation
  • 14. <latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit> ⇠⇤ =<latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit> Neural Network Threshold ˆuu Auto. Diff. ∂t ˆu = Θξ Library Include in cost function NN converged ξ∗ = ξ · ||Θ|| ||ut|| Solution Sparsity converged × × × × × × × × × × × keep set to zero keep ξ∗ Update cost function L = MSE(u, ˆu) + MSE(∂t ˆu, Θξ) + L1(ξ) = ... u ux uux u2 uxx Found solution ∂tu = uux − 0.1uxx 0 0 1 0 ... -0.1 0 uux uxx u ux u2 uxx Convergence ξ optimised MSE minimized c) Training the coefficient vector
  • 15. <latexit sha1_base64="1Gq7mrW1/ZKuQjtOjsnM1gDsGDU=">AAACBHicbZDJSgNBEIZ74hbjFvWYS2MQIkiYEUEvQtCLxwjZIBNCT6eSNOlZ6K4JCUMOXnwVLx4U8epDePNt7CwHTfyh4eOvKqrr9yIpNNr2t5VaW9/Y3EpvZ3Z29/YPsodHNR3GikOVhzJUDY9pkCKAKgqU0IgUMN+TUPcGd9N6fQhKizCo4DiCls96gegKztBY7WwubmNhdI5n9Ia6lT4go+4QeOKOxKSdzdtFeya6Cs4C8mShcjv75XZCHvsQIJdM66ZjR9hKmELBJUwybqwhYnzAetA0GDAfdCuZHTGhp8bp0G6ozAuQztzfEwnztR77nun0Gfb1cm1q/ldrxti9biUiiGKEgM8XdWNJMaTTRGhHKOAoxwYYV8L8lfI+U4yjyS1jQnCWT16F2kXRMfxwmS/dLuJIkxw5IQXikCtSIvekTKqEk0fyTF7Jm/VkvVjv1se8NWUtZo7JH1mfPysqlyg=</latexit> Dataset Neural Network Threshold ˆuu Auto. Diff. ∂t ˆu = Θξ Library Include in cost function NN converged ξ∗ = ξ · ||Θ|| ||ut|| Sparsity c × × × × × × × × × × × keep set to zero keep ξ∗ Update cost function Space Time Burgers equation ∂tu = uux − 0.1uxx L = MSE(u, ˆu) + MSE(∂t ˆu, Θξ) + L1(ξ) = ... u ux uux u2 uxx Space Time <latexit sha1_base64="f64HEF6znFEZoH5kmjcDbs/59Jo=">AAAB7XicbZBNSwMxEIZn61etX1WPXoJFqCBlVwQ9Fr14rGA/oF1KNk3b2OxmSWbFsvQ/ePGgiFf/jzf/jWm7B219IfDwzgyZeYNYCoOu++3kVlbX1jfym4Wt7Z3dveL+QcOoRDNeZ0oq3Qqo4VJEvI4CJW/FmtMwkLwZjG6m9eYj10ao6B7HMfdDOohEXzCK1mok5aczPO0WS27FnYksg5dBCTLVusWvTk+xJOQRMkmNaXtujH5KNQom+aTQSQyPKRvRAW9bjGjIjZ/Otp2QE+v0SF9p+yIkM/f3REpDY8ZhYDtDikOzWJua/9XaCfav/FREcYI8YvOP+okkqMj0dNITmjOUYwuUaWF3JWxINWVoAyrYELzFk5ehcV7xLN9dlKrXWRx5OIJjKIMHl1CFW6hBHRg8wDO8wpujnBfn3fmYt+acbOYQ/sj5/AHCpY6U</latexit> SolutionNoisy Data Regression Code available: github.com/PhIMaL L = LMSE + LReg + LL1<latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit><latexit sha1_base64="gUOXx4d83oxXFYgklynsP3UnEo8=">AAACMHicbVDLSsNAFJ3UV62vqEs3g0UQhJKIoBuhKKKLCvXRB7QhTKbTduhkEmYmQgn5JDd+im4UFHHrVzhps+jDAwNnzrmXe+/xQkalsqwPI7ewuLS8kl8trK1vbG6Z2zt1GUQCkxoOWCCaHpKEUU5qiipGmqEgyPcYaXiDy9RvPBEhacAf1TAkjo96nHYpRkpLrnnd9pHqY8TiSgLP4cTPjW8frhJ4NK3dk96cVnHtxDWLVskaAc4TOyNFkKHqmq/tToAjn3CFGZKyZVuhcmIkFMWMJIV2JEmI8AD1SEtTjnwinXh0cAIPtNKB3UDoxxUcqZMdMfKlHPqerkwXlbNeKv7ntSLVPXNiysNIEY7Hg7oRgyqAaXqwQwXBig01QVhQvSvEfSQQVjrjgg7Bnj15ntSPS7bmdyfF8kUWRx7sgX1wCGxwCsrgBlRBDWDwDN7AJ/gyXox349v4GZfmjKxnF0zB+P0DA3+pkA==</latexit> Neural network (~x, t)<latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit><latexit sha1_base64="lT4SfvKTT4nZSef6YVRDL9M85fI=">AAAB8nicbZDLSgMxFIYz9VbrrerSTbAIFaTMiKDLohuXFewFpkPJpJk2NJMMyZliGfoYblwo4tancefbmLaz0NYfAh//OYec84eJ4AZc99sprK1vbG4Vt0s7u3v7B+XDo5ZRqaasSZVQuhMSwwSXrAkcBOskmpE4FKwdju5m9faYacOVfIRJwoKYDCSPOCVgLb/aHTOaPU0v4LxXrrg1dy68Cl4OFZSr0St/dfuKpjGTQAUxxvfcBIKMaOBUsGmpmxqWEDoiA+ZblCRmJsjmK0/xmXX6OFLaPgl47v6eyEhszCQObWdMYGiWazPzv5qfQnQTZFwmKTBJFx9FqcCg8Ox+3OeaURATC4RqbnfFdEg0oWBTKtkQvOWTV6F1WfMsP1xV6rd5HEV0gk5RFXnoGtXRPWqgJqJIoWf0it4ccF6cd+dj0Vpw8plj9EfO5w++jZDj</latexit> ˆu<latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit><latexit sha1_base64="BGeEfkLOCpJ34NMiu4knM6UlhOc=">AAAB7nicbZBNSwMxEIZn/az1q+rRS7AInsquCHosevFYwX5Au5Rsmm1Ds9klmQhl6Y/w4kERr/4eb/4b03YP2vpC4OGdGTLzRpkUBn3/21tb39jc2i7tlHf39g8OK0fHLZNazXiTpTLVnYgaLoXiTRQoeSfTnCaR5O1ofDert5+4NiJVjzjJeJjQoRKxYBSd1e6NKOZ22q9U/Zo/F1mFoIAqFGr0K1+9QcpswhUySY3pBn6GYU41Cib5tNyzhmeUjemQdx0qmnAT5vN1p+TcOQMSp9o9hWTu/p7IaWLMJIlcZ0JxZJZrM/O/WtdifBPmQmUWuWKLj2IrCaZkdjsZCM0ZyokDyrRwuxI2opoydAmVXQjB8smr0LqsBY4frqr12yKOEpzCGVxAANdQh3toQBMYjOEZXuHNy7wX7937WLSuecXMCfyR9/kDq6+Pxg==</latexit> ⇠⇤ =<latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit><latexit sha1_base64="waOymetEs+AzOO0/zGH/BLksit4=">AAAB7XicbZDLSgMxFIbP1Futt6pLN8EiiIsyI4JuhKIblxXsBdqxZNJMG5tJhiQjlqHv4MaFIm59H3e+jZl2Ftr6Q+DjP+eQc/4g5kwb1/12CkvLK6trxfXSxubW9k55d6+pZaIIbRDJpWoHWFPOBG0YZjhtx4riKOC0FYyus3rrkSrNpLgz45j6ER4IFjKCjbWa3Sd2f3LZK1fcqjsVWgQvhwrkqvfKX92+JElEhSEca93x3Nj4KVaGEU4npW6iaYzJCA9ox6LAEdV+Ot12go6s00ehVPYJg6bu74kUR1qPo8B2RtgM9XwtM/+rdRITXvgpE3FiqCCzj8KEIyNRdjrqM0WJ4WMLmChmd0VkiBUmxgZUsiF48ycvQvO06lm+PavUrvI4inAAh3AMHpxDDW6gDg0g8ADP8ApvjnRenHfnY9ZacPKZffgj5/MH+eWOuA==</latexit> Neural Network Threshold ˆuu Auto. Diff. ∂t ˆu = Θξ Library Include in cost function NN converged ξ∗ = ξ · ||Θ|| ||ut|| Solution Sparsity converged × × × × × × × × × × × keep set to zero keep ξ∗ Update cost function L = MSE(u, ˆu) + MSE(∂t ˆu, Θξ) + L1(ξ) = ... u ux uux u2 uxx Found solution ∂tu = uux − 0.1uxx 0 0 1 0 ... -0.1 0 uux uxx u ux u2 uxx DeepMoD Model discovery neural networks DeepMoD Model discovery neural networks
  • 17. Resilience to Noise/ sampling size Relative error on coefficients <latexit sha1_base64="6yAhDb2lEN8ufJi3rjVOCio5Mf8=">AAACAnicbZDLSgMxFIYz9VbrbdSVuAkWQRDLjAi6EYpuXFawF2iHIZOmbWgmMyQn0jIUN76KGxeKuPUp3Pk2ppeFVn8IfPznHE7OH6WCa/C8Lye3sLi0vJJfLaytb2xuuds7NZ0YRVmVJiJRjYhoJrhkVeAgWCNVjMSRYPWofz2u1++Z0jyRdzBMWRCTruQdTglYK3T3TAj4Ep8YbMIBPsYtOaZsMBiFbtEreRPhv+DPoIhmqoTuZ6udUBMzCVQQrZu+l0KQEQWcCjYqtIxmKaF90mVNi5LETAfZ5IQRPrROG3cSZZ8EPHF/TmQk1noYR7YzJtDT87Wx+V+taaBzEWRcpgaYpNNFHSMwJHicB25zxSiIoQVCFbd/xbRHFKFgUyvYEPz5k/9C7bTkW749K5avZnHk0T46QEfIR+eojG5QBVURRQ/oCb2gV+fReXbenPdpa86ZzeyiX3I+vgEk2JX+</latexit> Burgers’ equation Applications in physics Higher order PDEs <latexit sha1_base64="89mN2eImzrIm0QzNLSbmbxofcBY=">AAACAHicbZDLSsNAFIYn9VbrLerChZvBIrixJCLqRii6cVnBXqANYTKdtEMnkzAXSQnZ+CpuXCji1sdw59s4bbPQ1gMzfPz/OcycP0gYlcpxvq3S0vLK6lp5vbKxubW9Y+/utWSsBSZNHLNYdAIkCaOcNBVVjHQSQVAUMNIORrcTv/1IhKQxf1DjhHgRGnAaUoyUkXz7QPsKXsMLqKH2U3hq7ixN09y3q07NmRZcBLeAKiiq4dtfvX6MdUS4wgxJ2XWdRHkZEopiRvJKT0uSIDxCA9I1yFFEpJdNF8jhsVH6MIyFOVzBqfp7IkORlOMoMJ0RUkM5703E/7yuVuGVl1GeaEU4nj0UagZVDCdpwD4VBCs2NoCwoOavEA+RQFiZzComBHd+5UVondVcw/fn1fpNEUcZHIIjcAJccAnq4A40QBNgkINn8ArerCfrxXq3PmatJauY2Qd/yvr8Aa06lS4=</latexit> t = 5 t = 7 t = 9 Ground truth Sampled Inferred y y y Coupled equations <latexit sha1_base64="oJZFq0o7Dpv+0FhHmocEH1HfGbM=">AAACJ3icbZDLSgMxFIYzXmu9jbp0EyxCXVhmRNCNUtSFywr2Ap0yZNJMG5rJDMkZtZS+jRtfxY2gIrr0TUzbWWjrgZCP/z+H5PxBIrgGx/my5uYXFpeWcyv51bX1jU17a7um41RRVqWxiFUjIJoJLlkVOAjWSBQjUSBYPehdjvz6HVOax/IW+glrRaQjecgpASP59nnqAz7DniSBIB5tx4A9wUIo4iufZzJO8SH2Hri5M+Eee4p3unDg2wWn5IwLz4KbQQFlVfHtV68d0zRiEqggWjddJ4HWgCjgVLBh3ks1SwjtkQ5rGpQkYro1GO85xPtGaeMwVuZIwGP198SARFr3o8B0RgS6etobif95zRTC09aAyyQFJunkoTAVGGI8Cg23uWIURN8AoYqbv2LaJYpQMNHmTQju9MqzUDsquYZvjgvliyyOHNpFe6iIXHSCyugaVVAVUfSIntEbereerBfrw/qctM5Z2cwO+lPW9w97rKPZ</latexit> <latexit sha1_base64="TZ48ZV1oiCE1tUaFN922vZ54mwQ=">AAACCXicbZDLSgMxFIYz9VbrrerSzcEiCGKZEUE3QtEuXFawF2iHIZOmbWjmQnLGUkq3bnwVNy4UcesbuPNtTNtZaOuBhI//P4fk/H4shUbb/rYyS8srq2vZ9dzG5tb2Tn53r6ajRDFeZZGMVMOnmksR8ioKlLwRK04DX/K637+Z+PUHrrSIwnscxtwNaDcUHcEoGsnLw8BDuAIoewNolblECgM4hb65T6AHCXj5gl20pwWL4KRQIGlVvPxXqx2xJOAhMkm1bjp2jO6IKhRM8nGulWgeU9anXd40GNKAa3c03WQMR0ZpQydS5oQIU/X3xIgGWg8D33QGFHt63puI/3nNBDuX7kiEcYI8ZLOHOokEjGASC7SF4gzl0ABlSpi/AutRRRma8HImBGd+5UWonRUdw3fnhdJ1GkeWHJBDckwcckFK5JZUSJUw8kieySt5s56sF+vd+pi1Zqx0Zp/8KevzB0yCluA=</latexit> u<latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit><latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit><latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit><latexit sha1_base64="0ivuOvsA1zGj29z/88YG+b8aLnI=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEeqx6MVjC/YD2lA220m7drMJuxuhhP4CLx4U8epP8ua/cdvmoK0vLDy8M8POvEEiuDau++0UNja3tneKu6W9/YPDo/LxSVvHqWLYYrGIVTegGgWX2DLcCOwmCmkUCOwEk7t5vfOESvNYPphpgn5ER5KHnFFjrWY6KFfcqrsQWQcvhwrkagzKX/1hzNIIpWGCat3z3MT4GVWGM4GzUj/VmFA2oSPsWZQ0Qu1ni0Vn5MI6QxLGyj5pyML9PZHRSOtpFNjOiJqxXq3Nzf9qvdSEN37GZZIalGz5UZgKYmIyv5oMuUJmxNQCZYrbXQkbU0WZsdmUbAje6snr0L6qepab15X6bR5HEc7gHC7BgxrU4R4a0AIGCM/wCm/Oo/PivDsfy9aCk8+cwh85nz/hr4z5</latexit> w<latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit><latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit><latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit><latexit sha1_base64="sGagZRpsBDQQXLOTtGoRB0Vi9Sc=">AAAB6HicbZBNS8NAEIYn9avWr6pHL4tF8FQSEfRY9OKxBfsBbSib7aRdu9mE3Y1SQn+BFw+KePUnefPfuG1z0NYXFh7emWFn3iARXBvX/XYKa+sbm1vF7dLO7t7+QfnwqKXjVDFssljEqhNQjYJLbBpuBHYShTQKBLaD8e2s3n5EpXks780kQT+iQ8lDzqixVuOpX664VXcusgpeDhXIVe+Xv3qDmKURSsME1brruYnxM6oMZwKnpV6qMaFsTIfYtShphNrP5otOyZl1BiSMlX3SkLn7eyKjkdaTKLCdETUjvVybmf/VuqkJr/2MyyQ1KNniozAVxMRkdjUZcIXMiIkFyhS3uxI2oooyY7Mp2RC85ZNXoXVR9Sw3Liu1mzyOIpzAKZyDB1dQgzuoQxMYIDzDK7w5D86L8+58LFoLTj5zDH/kfP4A5LeM+w==</latexit> :particle density :attractant density 2D equations
  • 18. Raw images Density field ut = 0.3uy + 0.01uxx + 0.01uyy<latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit><latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit><latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit><latexit sha1_base64="giCCDNoPIOmus3F40Yxqtlm2jVw=">AAACEnicbZBLS8NAEMc39VXrK+rRy2IRFKEkKuhFKHrxWME+oA1hs922SzebsA9pCPkMXvwqXjwo4tWTN7+N2zaH2jqw8Jv/zDA7/yBmVCrH+bEKS8srq2vF9dLG5tb2jr2715CRFpjUccQi0QqQJIxyUldUMdKKBUFhwEgzGN6O681HIiSN+INKYuKFqM9pj2KkjOTbJ9pX8Bo6lXOo/QSeGnJcg+lolM1kSZL5dtlkk4CL4OZQBnnUfPu7042wDglXmCEp264TKy9FQlHMSFbqaElihIeoT9oGOQqJ9NLJSRk8MkoX9iJhHldwos5OpCiUMgkD0xkiNZDztbH4X62tVe/KSymPtSIcTxf1NIMqgmN/YJcKghVLDCAsqPkrxAMkEFbGxZIxwZ0/eREaZxXX8P1FuXqT21EEB+AQHAMXXIIquAM1UAcYPIEX8AberWfr1fqwPqetBSuf2Qd/wvr6BTy+mhY=</latexit> Underlying AD equation Apply to real data … Model discovery from experimental data
  • 19. Single ParticleTracking Time xx Time Time Time Trajectory <latexit sha1_base64="A2yY/FcKHQddACwl6l5TaATnAyI=">AAACFXicbZDLSsQwFIZT7463qks3wUEQFGkHQTeC6MalguMMTGtJM+kYTNOSnMgMpS/hxldx40IRt4I738bMZaEz/hD4+M85nJw/zgXX4HnfztT0zOzc/MJiZWl5ZXXNXd+40ZlRlNVpJjLVjIlmgktWBw6CNXPFSBoL1ojvz/v1xgNTmmfyGno5C1PSkTzhlIC1InffRAVAifdwkChCC78sAiAmoiU2EeATHEhzW7NcdLtl5Fa9A28gPAn+CKpopMvI/QraGTUpk0AF0brlezmEBVHAqWBlJTCa5YTekw5rWZQkZTosBleVeMc6bZxkyj4JeOD+nihIqnUvjW1nSuBOj9f65n+1loHkOCy4zA0wSYeLEiMwZLgfEW5zxSiIngVCFbd/xfSO2HTABlmxIfjjJ0/CTe3At3x1WD09G8WxgLbQNtpFPjpCp+gCXaI6ougRPaNX9OY8OS/Ou/MxbJ1yRjOb6I+czx/MZJ6T</latexit> <latexit sha1_base64="l3iwXAx+BJVV3L+FIIt6mI0zRgc=">AAACAnicbZDLSsNAFIYn9VbrLepK3AwWQRBKIoJuhKIuXFawF2hDmEym7dDJJMyltITgxldx40IRtz6FO9/GaZuFtv4w8PGfczhz/iBhVCrH+bYKS8srq2vF9dLG5tb2jr2715CxFpjUccxi0QqQJIxyUldUMdJKBEFRwEgzGNxM6s0hEZLG/EGNE+JFqMdpl2KkjOXbB9pPVQav4C00NBpl8BQO/RBq6Ntlp+JMBRfBzaEMctV8+6sTxlhHhCvMkJRt10mUlyKhKGYkK3W0JAnCA9QjbYMcRUR66fSEDB4bJ4TdWJjHFZy6vydSFEk5jgLTGSHVl/O1iflfra1V99JLKU+0IhzPFnU1gyqGkzxgSAXBio0NICyo+SvEfSQQVia1kgnBnT95ERpnFdfw/Xm5ep3HUQSH4AicABdcgCq4AzVQBxg8gmfwCt6sJ+vFerc+Zq0FK5/ZB39kff4A+62V2w==</latexit> <latexit sha1_base64="q8SSRp0DvPa9XRci5Cdg/mAJUPE=">AAAB+nicbZDLSsNAFIZP6q3WW6pLN4NFcFUSEXQjFHXhsoK9QBvCZDpth04mYWaiLTGP4saFIm59Ene+jdM2C239YeDjP+dwzvxBzJnSjvNtFVZW19Y3ipulre2d3T27vN9UUSIJbZCIR7IdYEU5E7Shmea0HUuKw4DTVjC6ntZbD1QqFol7PYmpF+KBYH1GsDaWb5cTP9UZukQ3yNB4nCHfrjhVZya0DG4OFchV9+2vbi8iSUiFJhwr1XGdWHsplpoRTrNSN1E0xmSEB7RjUOCQKi+dnZ6hY+P0UD+S5gmNZu7viRSHSk3CwHSGWA/VYm1q/lfrJLp/4aVMxImmgswX9ROOdISmOaAek5RoPjGAiWTmVkSGWGKiTVolE4K7+OVlaJ5WXcN3Z5XaVR5HEQ7hCE7AhXOowS3UoQEEHuEZXuHNerJerHfrY95asPKZA/gj6/MHPD2TUg==</latexit> Random walk Advected random walk Persistant random walk x Density estimation Model discovery
  • 20. Time xx Time Time Time Trajectory <latexit sha1_base64="A2yY/FcKHQddACwl6l5TaATnAyI=">AAACFXicbZDLSsQwFIZT7463qks3wUEQFGkHQTeC6MalguMMTGtJM+kYTNOSnMgMpS/hxldx40IRt4I738bMZaEz/hD4+M85nJw/zgXX4HnfztT0zOzc/MJiZWl5ZXXNXd+40ZlRlNVpJjLVjIlmgktWBw6CNXPFSBoL1ojvz/v1xgNTmmfyGno5C1PSkTzhlIC1InffRAVAifdwkChCC78sAiAmoiU2EeATHEhzW7NcdLtl5Fa9A28gPAn+CKpopMvI/QraGTUpk0AF0brlezmEBVHAqWBlJTCa5YTekw5rWZQkZTosBleVeMc6bZxkyj4JeOD+nihIqnUvjW1nSuBOj9f65n+1loHkOCy4zA0wSYeLEiMwZLgfEW5zxSiIngVCFbd/xfSO2HTABlmxIfjjJ0/CTe3At3x1WD09G8WxgLbQNtpFPjpCp+gCXaI6ougRPaNX9OY8OS/Ou/MxbJ1yRjOb6I+czx/MZJ6T</latexit> <latexit sha1_base64="l3iwXAx+BJVV3L+FIIt6mI0zRgc=">AAACAnicbZDLSsNAFIYn9VbrLepK3AwWQRBKIoJuhKIuXFawF2hDmEym7dDJJMyltITgxldx40IRtz6FO9/GaZuFtv4w8PGfczhz/iBhVCrH+bYKS8srq2vF9dLG5tb2jr2715CxFpjUccxi0QqQJIxyUldUMdJKBEFRwEgzGNxM6s0hEZLG/EGNE+JFqMdpl2KkjOXbB9pPVQav4C00NBpl8BQO/RBq6Ntlp+JMBRfBzaEMctV8+6sTxlhHhCvMkJRt10mUlyKhKGYkK3W0JAnCA9QjbYMcRUR66fSEDB4bJ4TdWJjHFZy6vydSFEk5jgLTGSHVl/O1iflfra1V99JLKU+0IhzPFnU1gyqGkzxgSAXBio0NICyo+SvEfSQQVia1kgnBnT95ERpnFdfw/Xm5ep3HUQSH4AicABdcgCq4AzVQBxg8gmfwCt6sJ+vFerc+Zq0FK5/ZB39kff4A+62V2w==</latexit> <latexit sha1_base64="q8SSRp0DvPa9XRci5Cdg/mAJUPE=">AAAB+nicbZDLSsNAFIZP6q3WW6pLN4NFcFUSEXQjFHXhsoK9QBvCZDpth04mYWaiLTGP4saFIm59Ene+jdM2C239YeDjP+dwzvxBzJnSjvNtFVZW19Y3ipulre2d3T27vN9UUSIJbZCIR7IdYEU5E7Shmea0HUuKw4DTVjC6ntZbD1QqFol7PYmpF+KBYH1GsDaWb5cTP9UZukQ3yNB4nCHfrjhVZya0DG4OFchV9+2vbi8iSUiFJhwr1XGdWHsplpoRTrNSN1E0xmSEB7RjUOCQKi+dnZ6hY+P0UD+S5gmNZu7viRSHSk3CwHSGWA/VYm1q/lfrJLp/4aVMxImmgswX9ROOdISmOaAek5RoPjGAiWTmVkSGWGKiTVolE4K7+OVlaJ5WXcN3Z5XaVR5HEQ7hCE7AhXOowS3UoQEEHuEZXuHNerJerHfrY95asPKZA/gj6/MHPD2TUg==</latexit> Random walk Advected random walk Persistant random walk x Density estimation Model discovery Single ParticleTracking
  • 21. Density estimation:Temporal normalizing flows t z t x Latent spaceReal space x t Positional data Temporal Normalizing Flows (tNFs) extend NFs with a temporal component to estimate a time-dependent density evolution Code available on Github: https://github.com/PhIMaL Paper available on arXiv: 1912.09092
  • 22. Density estimation:Temporal normalizing flows t z t x Latent spaceReal space x t Positional data Temporal Normalizing Flows (tNFs) extend NFs with a temporal component to estimate a time-dependent density evolution tNFs allow discovery of PDEs with conservation constraints, e.g. Fokker-Planck, … Code available on Github: https://github.com/PhIMaL Paper available on arXiv: 1912.09092
  • 23. Code available on Github: https://github.com/PhIMaL DeepMoD Model discovery neural networks DeepMoD Model discovery neural networks Paper available on arXiv: 1904.08406 T. Chrysostomou (Intern) C. Le Scao ( Intern) A, Brandon-Bravo ( Engineer) G.-J. Both ( PhD) @GJ_Both @RemyKusters