SlideShare a Scribd company logo
1 of 45
1
The statistical physics approach to
the theory of learning
Typical learning curves in student / teacher models
www.cs.rug.nl/~biehl
Michael Biehl
APPIS 2023
1
The statistical physics approach to
the theory of learning
Typical learning curves in student / teacher models
www.cs.rug.nl/~biehl
Michael Biehl
APPIS 2023
•statistical physics of stochastic optimizaton
1
The statistical physics approach to
the theory of learning
Typical learning curves in student / teacher models
www.cs.rug.nl/~biehl
Michael Biehl
APPIS 2023
•statistical physics of stochastic optimizaton
•machine learning specifics, disorder average over data sets
1
The statistical physics approach to
the theory of learning
Typical learning curves in student / teacher models
www.cs.rug.nl/~biehl
Michael Biehl
APPIS 2023
•statistical physics of stochastic optimizaton
•machine learning specifics, disorder average over data sets
•a simplifying limit: training at high temperature
1
The statistical physics approach to
the theory of learning
Typical learning curves in student / teacher models
www.cs.rug.nl/~biehl
Michael Biehl
APPIS 2023
•statistical physics of stochastic optimizaton
•machine learning specifics, disorder average over data sets
•a simplifying limit: training at high temperature
•student / teacher models
1
The statistical physics approach to
the theory of learning
Typical learning curves in student / teacher models
www.cs.rug.nl/~biehl
Michael Biehl
APPIS 2023
•statistical physics of stochastic optimizaton
•machine learning specifics, disorder average over data sets
•a simplifying limit: training at high temperature
•student / teacher models
•example: phase transitions in (shallow) layered neural networks
2
Statistical Physics of Neural Networks
John Hopfield
Neural Networks and physical systems with emergent
collective computational abilities
PNAS 79(8): 2554, 1982
[activity of model neurons for given synaptic weights]
2
Statistical Physics of Neural Networks
John Hopfield
Neural Networks and physical systems with emergent
collective computational abilities
PNAS 79(8): 2554, 1982
[activity of model neurons for given synaptic weights]
Elizabeth Gardner (1957-1988)
The space of interactions in neural networks
J. Phys. A 21: 257, 1988
[synaptic weights determined for given activity patterns]
3
stochastic optimization
objective/cost/ energy function , e.g. (later: )
consider stochastic optimization process, for example:
H(w) w ∈ ℝN
N → ∞
3
stochastic optimization
objective/cost/ energy function , e.g. (later: )
consider stochastic optimization process, for example:
H(w) w ∈ ℝN
N → ∞
Metropolis-like updates: small random changes of
accepted with probability
Δw w
min{1, exp[−βΔH]}
3
stochastic optimization
objective/cost/ energy function , e.g. (later: )
consider stochastic optimization process, for example:
H(w) w ∈ ℝN
N → ∞
Metropolis-like updates: small random changes of
accepted with probability
Δw w
min{1, exp[−βΔH]}
Langevin dynamics: noisy gradient descent
∂w
∂t
= − ∇wH(w) + f(t)
⟨fj(t)fk(s)⟩ =
2
β
δjkδ(t − s)
with delta-correlated noise:
3
stochastic optimization
objective/cost/ energy function , e.g. (later: )
consider stochastic optimization process, for example:
H(w) w ∈ ℝN
N → ∞
Metropolis-like updates: small random changes of
accepted with probability
Δw w
min{1, exp[−βΔH]}
Langevin dynamics: noisy gradient descent
∂w
∂t
= − ∇wH(w) + f(t)
⟨fj(t)fk(s)⟩ =
2
β
δjkδ(t − s)
with delta-correlated noise:
… acceptance rate for uphill moves in Metropolis algorithms
... noise level, i.e. random deviation from gradient
… “how serious we are about minimizing ”
H
temperature-like parameter controls
thermal equilibrium
stationary density of configurations:
normalization:
Zustandssumme, partition function
4
P(w) =
1
Z
exp [−βH(w)]
Z =
∫
dN
w exp [−βH(w)]
thermal equilibrium
stationary density of configurations:
normalization:
Zustandssumme, partition function
Gibbs-Boltzmann density of states
• physics: thermal equilibrium of a physical system at temperature T
• optimization: formal equilibrium situation, control parameter T
4
P(w) =
1
Z
exp [−βH(w)]
Z =
∫
dN
w exp [−βH(w)]
thermal equilibrium
stationary density of configurations:
normalization:
Zustandssumme, partition function
Gibbs-Boltzmann density of states
• physics: thermal equilibrium of a physical system at temperature T
• optimization: formal equilibrium situation, control parameter T
4
P(w) =
1
Z
exp [−βH(w)]
• thermal averages, e.g.
equilibrium properties given by (derivatives of) ln Z
E = ⟨H⟩T
=
∫
dN
w H(w) P(w) = −
∂
∂β
ln Z
Z =
∫
dN
w exp [−βH(w)]
5
~ volume of states with energy E
Z =
∫
dN
w exp[−β(Hw)] =
∫
dE
∫
dN
w δ[H(w) − E] e−βE
free energy
5
~ volume of states with energy E
Z =
∫
dN
w exp[−β(Hw)] =
∫
dE
∫
dN
w δ[H(w) − E] e−βE
assume extensive energy , for
E = Ne N → ∞
Z =
∫
dE exp [−Nβ (e − s(e)/β)]
entropy ,
s(E)
f = e − s/β ∼ − ln Z/(βN)
dominated by the minimum of the
free energy
free energy
5
~ volume of states with energy E
Z =
∫
dN
w exp[−β(Hw)] =
∫
dE
∫
dN
w δ[H(w) − E] e−βE
assume extensive energy , for
E = Ne N → ∞
Z =
∫
dE exp [−Nβ (e − s(e)/β)]
entropy ,
s(E)
f = e − s/β ∼ − ln Z/(βN)
dominated by the minimum of the
free energy
free energy
controls the competition between
minimization of energy e and
maximization of entropy s(e)
T = 1/β
6
machine learning
ID = {ξμ
, τμ
= τ(ξμ
)}
P
μ=1
H(w) =
P
∑
μ=1
ϵ(σμ
, τμ
)
specifically:
extensive ( ) for
∼ N P = αN
compares student outputs σμ
= σ(ξμ
) and targets τμ
= τ(ξμ
)
energy: defined with respect a given data set
6
machine learning
ID = {ξμ
, τμ
= τ(ξμ
)}
P
μ=1
H(w) =
P
∑
μ=1
ϵ(σμ
, τμ
)
specifically:
extensive ( ) for
∼ N P = αN
compares student outputs σμ
= σ(ξμ
) and targets τμ
= τ(ξμ
)
energy: defined with respect a given data set
6
machine learning
ID = {ξμ
, τμ
= τ(ξμ
)}
P
μ=1
H(w) =
P
∑
μ=1
ϵ(σμ
, τμ
)
typical results on average over data sets ID
•specific input density, e.g. i.i.d. zero mean, unit variance ξμ
j
•training labels provided by teacher network
τμ
, consider
specifically:
extensive ( ) for
∼ N P = αN
compares student outputs σμ
= σ(ξμ
) and targets τμ
= τ(ξμ
)
energy: defined with respect a given data set
6
machine learning
ID = {ξμ
, τμ
= τ(ξμ
)}
P
μ=1
H(w) =
P
∑
μ=1
ϵ(σμ
, τμ
)
typical results on average over data sets ID
•specific input density, e.g. i.i.d. zero mean, unit variance ξμ
j
•training labels provided by teacher network
τμ
, consider
disorder average:
quenched free energy ∼ ⟨ln Z⟩ID
technically difficult for general T = 1/β
specifically:
extensive ( ) for
∼ N P = αN
compares student outputs σμ
= σ(ξμ
) and targets τμ
= τ(ξμ
)
energy: defined with respect a given data set
6
machine learning
ID = {ξμ
, τμ
= τ(ξμ
)}
P
μ=1
H(w) =
P
∑
μ=1
ϵ(σμ
, τμ
)
typical results on average over data sets ID
•specific input density, e.g. i.i.d. zero mean, unit variance ξμ
j
•training labels provided by teacher network
τμ
, consider
disorder average:
quenched free energy ∼ ⟨ln Z⟩ID
technically difficult for general T = 1/β
specifically:
e.g. by means of the replica trick/method Giorgio Parisi, Nobel 2021
extensive ( ) for
∼ N P = αN
compares student outputs σμ
= σ(ξμ
) and targets τμ
= τ(ξμ
)
energy: defined with respect a given data set
7
high temperature limit
a simplifying limit: training at high temperature
lim
β→0
: ⟨ln Z⟩ID
= ln ⟨Z⟩ID ⟨H(w) ⟩ID
= P ⟨ϵ(σ, τ)⟩ξ
= P ϵg
generalization error
7
high temperature limit
a simplifying limit: training at high temperature
lim
β→0
: ⟨ln Z⟩ID
= ln ⟨Z⟩ID
βf = β (P/N) ϵg − s(ϵg)
⟨H(w) ⟩ID
= P ⟨ϵ(σ, τ)⟩ξ
= P ϵg
generalization error
7
high temperature limit
a simplifying limit: training at high temperature
lim
β→0
: ⟨ln Z⟩ID
= ln ⟨Z⟩ID
βf = β (P/N) ϵg − s(ϵg)
⟨H(w) ⟩ID
= P ⟨ϵ(σ, τ)⟩ξ
= P ϵg
generalization error
β → 0
P/N → ∞
⏟
α = 𝒪(1)
“learn almost nothing from
infinitely many examples”
7
high temperature limit
a simplifying limit: training at high temperature
lim
β→0
: ⟨ln Z⟩ID
= ln ⟨Z⟩ID
βf = β (P/N) ϵg − s(ϵg)
⟨H(w) ⟩ID
= P ⟨ϵ(σ, τ)⟩ξ
= P ϵg
generalization error
β → 0
P/N → ∞
⏟
α = 𝒪(1)
“learn almost nothing from
infinitely many examples”
min. free energy typical learning curve ϵg(α)
7
high temperature limit
a simplifying limit: training at high temperature
lim
β→0
: ⟨ln Z⟩ID
= ln ⟨Z⟩ID
βf = β (P/N) ϵg − s(ϵg)
⟨H(w) ⟩ID
= P ⟨ϵ(σ, τ)⟩ξ
= P ϵg
generalization error
β → 0
P/N → ∞
⏟
α = 𝒪(1)
“learn almost nothing from
infinitely many examples”
limitations:
- training error and generalization error cannot be distinguished
- number of examples and training temperature are coupled
- (at best) qualitative agreement with low temperature results
min. free energy typical learning curve ϵg(α)
8
student/teacher scenarios
example system: soft-committee machines (SCM)
adaptive student N-dim. inputs
<latexit
sha1_base64="EWEUTU/uT8q6Rkb2wo5Q65mhUMs=">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</latexit>
=
K
X
k=1
g
✓
wk · ⇠
p
N
◆
8
student/teacher scenarios
example system: soft-committee machines (SCM)
adaptive student N-dim. inputs
•non-linear hidden unit activations , fixed linear output
g(z)
<latexit
sha1_base64="EWEUTU/uT8q6Rkb2wo5Q65mhUMs=">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</latexit>
=
K
X
k=1
g
✓
wk · ⇠
p
N
◆
8
•complexity (mis-)match: vs. hidden units, here
K M K = M
student/teacher scenarios
example system: soft-committee machines (SCM)
adaptive student N-dim. inputs teacher parameterizes target
? ? ? ? ? ? ?
<latexit
sha1_base64="ALwOwp1y3TncZZzQCxrhKlQLkC0=">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</latexit>
⌧ =
M
X
m=1
g
✓
w⇤
m · ⇠
p
N
◆
•non-linear hidden unit activations , fixed linear output
g(z)
<latexit
sha1_base64="EWEUTU/uT8q6Rkb2wo5Q65mhUMs=">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</latexit>
=
K
X
k=1
g
✓
wk · ⇠
p
N
◆
8
•complexity (mis-)match: vs. hidden units, here
K M K = M
student/teacher scenarios
example system: soft-committee machines (SCM)
adaptive student N-dim. inputs teacher parameterizes target
? ? ? ? ? ? ?
<latexit
sha1_base64="ALwOwp1y3TncZZzQCxrhKlQLkC0=">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</latexit>
⌧ =
M
X
m=1
g
✓
w⇤
m · ⇠
p
N
◆
•non-linear hidden unit activations , fixed linear output
g(z)
•given determine weights
ID = {ξμ
, τμ
= τ(ξμ
)}
P
μ=1
W = {wk}
K
k=1
H(W) =
1
P
P
∑
μ=1
ϵ(σμ
, τμ
) =
1
P
P
∑
μ=1
1
2
(σμ
− τμ
)2
<latexit
sha1_base64="EWEUTU/uT8q6Rkb2wo5Q65mhUMs=">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</latexit>
=
K
X
k=1
g
✓
wk · ⇠
p
N
◆
by minimizing costs
9
SCM student/teacher
thermodynamic limit Central Limit Theorem (CLT) :
N → ∞
xk =
wk ⋅ ξ
N
x*
m =
w*
m ⋅ ξ
N
become zero mean Gaussians
with -dim covariance matrix
(M + K) × (M + K)
9
SCM student/teacher
thermodynamic limit Central Limit Theorem (CLT) :
N → ∞
xk =
wk ⋅ ξ
N
x*
m =
w*
m ⋅ ξ
N
become zero mean Gaussians
with -dim covariance matrix
(M + K) × (M + K)
C =
2
6
6
6
6
6
6
6
6
4
T11 T12 . . . T1M R11 R21 . . . RK1
.
.
.
.
.
.
...
.
.
.
.
.
.
.
.
.
...
.
.
.
TM1 TM2 . . . TMM R1M R2M . . . RKM
R11 R12 . . . R1M Q11 Q12 . . . Q1K
.
.
.
.
.
.
...
.
.
.
.
.
.
.
.
.
...
.
.
.
RK1 RK2 . . . RKM QK1 QK2 . . . QKK
3
7
7
7
7
7
7
7
7
5
=

T R
R>
Q
Rim = wi · w⇤
m/N
Qik = wi · wk/N
Tmn = w⇤
m · w⇤
n/N
order parameters: model parameters:
macroscopic
properties of
the system
Qik = Qki
Tmn = Tnm
9
SCM student/teacher
thermodynamic limit Central Limit Theorem (CLT) :
N → ∞
xk =
wk ⋅ ξ
N
x*
m =
w*
m ⋅ ξ
N
become zero mean Gaussians
with -dim covariance matrix
(M + K) × (M + K)
C =
2
6
6
6
6
6
6
6
6
4
T11 T12 . . . T1M R11 R21 . . . RK1
.
.
.
.
.
.
...
.
.
.
.
.
.
.
.
.
...
.
.
.
TM1 TM2 . . . TMM R1M R2M . . . RKM
R11 R12 . . . R1M Q11 Q12 . . . Q1K
.
.
.
.
.
.
...
.
.
.
.
.
.
.
.
.
...
.
.
.
RK1 RK2 . . . RKM QK1 QK2 . . . QKK
3
7
7
7
7
7
7
7
7
5
=

T R
R>
Q
Rim = wi · w⇤
m/N
Qik = wi · wk/N
Tmn = w⇤
m · w⇤
n/N
order parameters: model parameters:
macroscopic
properties of
the system
⟨…⟩ξ
→ ⟨…⟩
{xk,x*
m}
averages:
Qik = Qki
Tmn = Tnm
Gaussian integrals!
10
simplification: orthonormal teacher vectors, isotropic input density
reflects permutation symmetry, allows for hidden unit specialization
Tij =
⇢
1 for i = j
0 else,
Rij =
⇢
R for i = j
S else,
Qij =
⇢
1 for i = j
C else.
<latexit
sha1_base64="z3U/1x66FQ8CCAKv5dCLWIcbiuE=">AAADPXicpVI7b9RAEF6bQBLzukBJMyICUSDLTiSSJlIgDWVel0S6PZ3We+O7TdZra3eNOFm+X5Ffk4aCf0BHR0PBQ4guLeu7gMhDCMRIK3365vHNzE5SSGFsFL33/Gsz12/Mzs0HN2/dvnO3tXBvz+Sl5tjmucz1QcIMSqGwbYWVeFBoZFkicT852mj8+69QG5GrXTsqsJuxgRKp4Mw6qrfg7ez2KnFYwxoAlZhaWgFNcCBUxbRmoxoqKesAYngMNEvy11Wa63ENYu0QKAUIIPrlQWnwad3QAVBU/Z8VqBaDoQ2DadR4PK6D7b8S3b5SdD6AnX/XdKJb/zGpE904Jxr+QbTXWozCaGJwGcRnYHH92ZfjF8/fft/std7Rfs7LDJXlkhnTiaPCdl1ZK7jEOqClwYLxIzbAjoOKZWi61eT3a3jkmD64Zt1TFibs7xkVy4wZZYmLzJgdmou+hrzK1yltutqthCpKi4pPhdJSgs2hOSXoC43cypEDjGvhegU+ZJpx6w6uWUJ8ceTLYG8pjJfDpS23jVUytTnygDwkT0hMVsg6eUk2SZtw78T74H3yPvtv/I/+V//bNNT3znLuk3Pmn/4AGwYIbw==</latexit>
SCM with sigmoidal activation
10
simplification: orthonormal teacher vectors, isotropic input density
reflects permutation symmetry, allows for hidden unit specialization
Tij =
⇢
1 for i = j
0 else,
Rij =
⇢
R for i = j
S else,
Qij =
⇢
1 for i = j
C else.
<latexit
sha1_base64="z3U/1x66FQ8CCAKv5dCLWIcbiuE=">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</latexit>
SCM with sigmoidal activation
✏g =
1
K
⇢
1
3
+
K 1
⇡

sin 1
✓
C
2
◆
2 sin 1
✓
S
2
◆
2
⇡
sin 1
✓
R
2
◆
<latexit
sha1_base64="050svsyqr1f80CEz0aVNkCq3F3g=">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</latexit>
=
⟨
1
2
(σ − τ)2
⟩
ξ
s =
1
2
ln det[ C ] (+ constant)
s =
1
2
ln
h
1+(K 1)C ((R S)+KS)
2
i
+K 1
2 ln
⇥
1 C (R S)2
⇤
<latexit
sha1_base64="R1D/dvB51gM9AtxPyLBvGiIN87s=">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</latexit>
(+ constant)
10
simplification: orthonormal teacher vectors, isotropic input density
reflects permutation symmetry, allows for hidden unit specialization
Tij =
⇢
1 for i = j
0 else,
Rij =
⇢
R for i = j
S else,
Qij =
⇢
1 for i = j
C else.
<latexit
sha1_base64="z3U/1x66FQ8CCAKv5dCLWIcbiuE=">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</latexit>
SCM with sigmoidal activation
✏g =
1
K
⇢
1
3
+
K 1
⇡

sin 1
✓
C
2
◆
2 sin 1
✓
S
2
◆
2
⇡
sin 1
✓
R
2
◆
<latexit
sha1_base64="050svsyqr1f80CEz0aVNkCq3F3g=">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</latexit>
=
⟨
1
2
(σ − τ)2
⟩
ξ
s =
1
2
ln det[ C ] (+ constant)
s =
1
2
ln
h
1+(K 1)C ((R S)+KS)
2
i
+K 1
2 ln
⇥
1 C (R S)2
⇤
<latexit
sha1_base64="R1D/dvB51gM9AtxPyLBvGiIN87s=">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</latexit>
(+ constant)
David Saad, Sara Solla
Robert Urbanczik
10
simplification: orthonormal teacher vectors, isotropic input density
reflects permutation symmetry, allows for hidden unit specialization
Tij =
⇢
1 for i = j
0 else,
Rij =
⇢
R for i = j
S else,
Qij =
⇢
1 for i = j
C else.
<latexit
sha1_base64="z3U/1x66FQ8CCAKv5dCLWIcbiuE=">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</latexit>
SCM with sigmoidal activation
✏g =
1
K
⇢
1
3
+
K 1
⇡

sin 1
✓
C
2
◆
2 sin 1
✓
S
2
◆
2
⇡
sin 1
✓
R
2
◆
<latexit
sha1_base64="050svsyqr1f80CEz0aVNkCq3F3g=">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</latexit>
=
⟨
1
2
(σ − τ)2
⟩
ξ
s =
1
2
ln det[ C ] (+ constant)
s =
1
2
ln
h
1+(K 1)C ((R S)+KS)
2
i
+K 1
2 ln
⇥
1 C (R S)2
⇤
<latexit
sha1_base64="R1D/dvB51gM9AtxPyLBvGiIN87s=">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</latexit>
(+ constant)
minimize (βf ) = α ϵg − s(ϵg) →
R(α)
C(α)
S(α)
→ ϵg(α)
success of learning
as a function of
the training set size
David Saad, Sara Solla
Robert Urbanczik
11
↵
<
latexit
sha1_base64="+wSBPeL8nxBdvzPXA2qswhGhfpg=">AAAB7XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae0oUy2m3btZhN2N0IJ/Q9ePCji1f/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqKGvSWMSqE6BmgkvWNNwI1kkUwygQrB2Mb2d++4kpzWP5YCYJ8yMcSh5yisZKrR6KZIT9csWtunOQVeLlpAI5Gv3yV28Q0zRi0lCBWnc9NzF+hspwKti01Es1S5COcci6lkqMmPaz+bVTcmaVAQljZUsaMld/T2QYaT2JAtsZoRnpZW8m/ud1UxNe+xmXSWqYpItFYSqIicnsdTLgilEjJpYgVdzeSugIFVJjAyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAECo/wDK/w5sTOi/PufCxaC04+cwx/4Hz+AIzPjxw=</latexit>
R
<
latexit
sha1_base64="cVRUNBy/RTcU6LUbsjbBwonoaeo=">AAAB6HicbVDLTgJBEOzFF+IL9ehlIjHxRHbRRI9ELx7ByCOBDZkdemFkdnYzM2tCCF/gxYPGePWTvPk3DrAHBSvppFLVne6uIBFcG9f9dnJr6xubW/ntws7u3v5B8fCoqeNUMWywWMSqHVCNgktsGG4EthOFNAoEtoLR7cxvPaHSPJYPZpygH9GB5CFn1Fipft8rltyyOwdZJV5GSpCh1it+dfsxSyOUhgmqdcdzE+NPqDKcCZwWuqnGhLIRHWDHUkkj1P5kfuiUnFmlT8JY2ZKGzNXfExMaaT2OAtsZUTPUy95M/M/rpCa89idcJqlByRaLwlQQE5PZ16TPFTIjxpZQpri9lbAhVZQZm03BhuAtv7xKmpWyd1Gu1C9L1ZssjjycwCmcgwdXUIU7qEEDGCA8wyu8OY/Oi/PufCxac042cwx/4Hz+AK3vjNo=</latexit>
S
<
latexit
sha1_base64="vFchJGr6Z+gyWiveB04FdIL/myI=">AAAB6HicbVDLTgJBEOzFF+IL9ehlIjHxRHbRRI9ELx4hyiOBDZkdemFkdnYzM2tCCF/gxYPGePWTvPk3DrAHBSvppFLVne6uIBFcG9f9dnJr6xubW/ntws7u3v5B8fCoqeNUMWywWMSqHVCNgktsGG4EthOFNAoEtoLR7cxvPaHSPJYPZpygH9GB5CFn1Fipft8rltyyOwdZJV5GSpCh1it+dfsxSyOUhgmqdcdzE+NPqDKcCZwWuqnGhLIRHWDHUkkj1P5kfuiUnFmlT8JY2ZKGzNXfExMaaT2OAtsZUTPUy95M/M/rpCa89idcJqlByRaLwlQQE5PZ16TPFTIjxpZQpri9lbAhVZQZm03BhuAtv7xKmpWyd1Gu1C9L1ZssjjycwCmcgwdXUIU7qEEDGCA8wyu8OY/Oi/PufCxac042cwx/4Hz+AK9zjNs=</latexit>
R = S
<latexit
sha1_base64="nDUP4fccke/FNLKaaM8Wqz9O1M8=">AAAB6nicbVDLSgNBEOz1GeMr6tHLYBA8hd0o6EUIevEYjXlAsoTZSW8yZHZ2mZkVQsgnePGgiFe/yJt/4yTZgyYWNBRV3XR3BYng2rjut7Oyura+sZnbym/v7O7tFw4OGzpOFcM6i0WsWgHVKLjEuuFGYCtRSKNAYDMY3k795hMqzWP5aEYJ+hHtSx5yRo2Vag/XtW6h6JbcGcgy8TJShAzVbuGr04tZGqE0TFCt256bGH9MleFM4CTfSTUmlA1pH9uWShqh9sezUyfk1Co9EsbKljRkpv6eGNNI61EU2M6ImoFe9Kbif147NeGVP+YySQ1KNl8UpoKYmEz/Jj2ukBkxsoQyxe2thA2ooszYdPI2BG/x5WXSKJe881L5/qJYucniyMExnMAZeHAJFbiDKtSBQR+e4RXeHOG8OO/Ox7x1xclmjuAPnM8f0umNfg==</latexit>
✏g
<latexit
sha1_base64="mglHXcqwu+eocCx6ul5cTySUvNg=">AAAB8XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae2oWy2k3bpZhN2N0IJ/RdePCji1X/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqGDZZLGLVCahGwSU2DTcCO4lCGgUC28H4dua3n1BpHssHM0nQj+hQ8pAzaqz02MNEcxHL/rBfrrhVdw6ySrycVCBHo1/+6g1ilkYoDRNU667nJsbPqDKcCZyWeqnGhLIxHWLXUkkj1H42v3hKzqwyIGGsbElD5urviYxGWk+iwHZG1Iz0sjcT//O6qQmv/YzLJDUo2WJRmApiYjJ7nwy4QmbExBLKFLe3EjaiijJjQyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAEBhKe4RXeHO28OO/Ox6K14OQzx/AHzucPyzeQ/g==</latexit>
↵
<
latexit
sha1_base64="+wSBPeL8nxBdvzPXA2qswhGhfpg=">AAAB7XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae0oUy2m3btZhN2N0IJ/Q9ePCji1f/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqKGvSWMSqE6BmgkvWNNwI1kkUwygQrB2Mb2d++4kpzWP5YCYJ8yMcSh5yisZKrR6KZIT9csWtunOQVeLlpAI5Gv3yV28Q0zRi0lCBWnc9NzF+hspwKti01Es1S5COcci6lkqMmPaz+bVTcmaVAQljZUsaMld/T2QYaT2JAtsZoRnpZW8m/ud1UxNe+xmXSWqYpItFYSqIicnsdTLgilEjJpYgVdzeSugIFVJjAyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAECo/wDK/w5sTOi/PufCxaC04+cwx/4Hz+AIzPjxw=</latexit>
K=M=2
phase transitions: hidden unit specialization
SCM with sigmoidal activation
continuous
specialization
transition
11
↵
<
latexit
sha1_base64="+wSBPeL8nxBdvzPXA2qswhGhfpg=">AAAB7XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae0oUy2m3btZhN2N0IJ/Q9ePCji1f/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqKGvSWMSqE6BmgkvWNNwI1kkUwygQrB2Mb2d++4kpzWP5YCYJ8yMcSh5yisZKrR6KZIT9csWtunOQVeLlpAI5Gv3yV28Q0zRi0lCBWnc9NzF+hspwKti01Es1S5COcci6lkqMmPaz+bVTcmaVAQljZUsaMld/T2QYaT2JAtsZoRnpZW8m/ud1UxNe+xmXSWqYpItFYSqIicnsdTLgilEjJpYgVdzeSugIFVJjAyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAECo/wDK/w5sTOi/PufCxaC04+cwx/4Hz+AIzPjxw=</latexit>
R
<
latexit
sha1_base64="cVRUNBy/RTcU6LUbsjbBwonoaeo=">AAAB6HicbVDLTgJBEOzFF+IL9ehlIjHxRHbRRI9ELx7ByCOBDZkdemFkdnYzM2tCCF/gxYPGePWTvPk3DrAHBSvppFLVne6uIBFcG9f9dnJr6xubW/ntws7u3v5B8fCoqeNUMWywWMSqHVCNgktsGG4EthOFNAoEtoLR7cxvPaHSPJYPZpygH9GB5CFn1Fipft8rltyyOwdZJV5GSpCh1it+dfsxSyOUhgmqdcdzE+NPqDKcCZwWuqnGhLIRHWDHUkkj1P5kfuiUnFmlT8JY2ZKGzNXfExMaaT2OAtsZUTPUy95M/M/rpCa89idcJqlByRaLwlQQE5PZ16TPFTIjxpZQpri9lbAhVZQZm03BhuAtv7xKmpWyd1Gu1C9L1ZssjjycwCmcgwdXUIU7qEEDGCA8wyu8OY/Oi/PufCxac042cwx/4Hz+AK3vjNo=</latexit>
S
<
latexit
sha1_base64="vFchJGr6Z+gyWiveB04FdIL/myI=">AAAB6HicbVDLTgJBEOzFF+IL9ehlIjHxRHbRRI9ELx4hyiOBDZkdemFkdnYzM2tCCF/gxYPGePWTvPk3DrAHBSvppFLVne6uIBFcG9f9dnJr6xubW/ntws7u3v5B8fCoqeNUMWywWMSqHVCNgktsGG4EthOFNAoEtoLR7cxvPaHSPJYPZpygH9GB5CFn1Fipft8rltyyOwdZJV5GSpCh1it+dfsxSyOUhgmqdcdzE+NPqDKcCZwWuqnGhLIRHWDHUkkj1P5kfuiUnFmlT8JY2ZKGzNXfExMaaT2OAtsZUTPUy95M/M/rpCa89idcJqlByRaLwlQQE5PZ16TPFTIjxpZQpri9lbAhVZQZm03BhuAtv7xKmpWyd1Gu1C9L1ZssjjycwCmcgwdXUIU7qEEDGCA8wyu8OY/Oi/PufCxac042cwx/4Hz+AK9zjNs=</latexit>
R = S
<latexit
sha1_base64="nDUP4fccke/FNLKaaM8Wqz9O1M8=">AAAB6nicbVDLSgNBEOz1GeMr6tHLYBA8hd0o6EUIevEYjXlAsoTZSW8yZHZ2mZkVQsgnePGgiFe/yJt/4yTZgyYWNBRV3XR3BYng2rjut7Oyura+sZnbym/v7O7tFw4OGzpOFcM6i0WsWgHVKLjEuuFGYCtRSKNAYDMY3k795hMqzWP5aEYJ+hHtSx5yRo2Vag/XtW6h6JbcGcgy8TJShAzVbuGr04tZGqE0TFCt256bGH9MleFM4CTfSTUmlA1pH9uWShqh9sezUyfk1Co9EsbKljRkpv6eGNNI61EU2M6ImoFe9Kbif147NeGVP+YySQ1KNl8UpoKYmEz/Jj2ukBkxsoQyxe2thA2ooszYdPI2BG/x5WXSKJe881L5/qJYucniyMExnMAZeHAJFbiDKtSBQR+e4RXeHOG8OO/Ox7x1xclmjuAPnM8f0umNfg==</latexit>
✏g
<latexit
sha1_base64="mglHXcqwu+eocCx6ul5cTySUvNg=">AAAB8XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae2oWy2k3bpZhN2N0IJ/RdePCji1X/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqGDZZLGLVCahGwSU2DTcCO4lCGgUC28H4dua3n1BpHssHM0nQj+hQ8pAzaqz02MNEcxHL/rBfrrhVdw6ySrycVCBHo1/+6g1ilkYoDRNU667nJsbPqDKcCZyWeqnGhLIxHWLXUkkj1H42v3hKzqwyIGGsbElD5urviYxGWk+iwHZG1Iz0sjcT//O6qQmv/YzLJDUo2WJRmApiYjJ7nwy4QmbExBLKFLe3EjaiijJjQyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAEBhKe4RXeHO28OO/Ox6K14OQzx/AHzucPyzeQ/g==</latexit>
↵
<
latexit
sha1_base64="+wSBPeL8nxBdvzPXA2qswhGhfpg=">AAAB7XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae0oUy2m3btZhN2N0IJ/Q9ePCji1f/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqKGvSWMSqE6BmgkvWNNwI1kkUwygQrB2Mb2d++4kpzWP5YCYJ8yMcSh5yisZKrR6KZIT9csWtunOQVeLlpAI5Gv3yV28Q0zRi0lCBWnc9NzF+hspwKti01Es1S5COcci6lkqMmPaz+bVTcmaVAQljZUsaMld/T2QYaT2JAtsZoRnpZW8m/ud1UxNe+xmXSWqYpItFYSqIicnsdTLgilEjJpYgVdzeSugIFVJjAyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAECo/wDK/w5sTOi/PufCxaC04+cwx/4Hz+AIzPjxw=</latexit>
K=M=2
phase transitions: hidden unit specialization
SCM with sigmoidal activation
↵
<
latexit
sha1_base64="+wSBPeL8nxBdvzPXA2qswhGhfpg=">AAAB7XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae0oUy2m3btZhN2N0IJ/Q9ePCji1f/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqKGvSWMSqE6BmgkvWNNwI1kkUwygQrB2Mb2d++4kpzWP5YCYJ8yMcSh5yisZKrR6KZIT9csWtunOQVeLlpAI5Gv3yV28Q0zRi0lCBWnc9NzF+hspwKti01Es1S5COcci6lkqMmPaz+bVTcmaVAQljZUsaMld/T2QYaT2JAtsZoRnpZW8m/ud1UxNe+xmXSWqYpItFYSqIicnsdTLgilEjJpYgVdzeSugIFVJjAyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAECo/wDK/w5sTOi/PufCxaC04+cwx/4Hz+AIzPjxw=</latexit>
R
<
latexit
sha1_base64="cVRUNBy/RTcU6LUbsjbBwonoaeo=">AAAB6HicbVDLTgJBEOzFF+IL9ehlIjHxRHbRRI9ELx7ByCOBDZkdemFkdnYzM2tCCF/gxYPGePWTvPk3DrAHBSvppFLVne6uIBFcG9f9dnJr6xubW/ntws7u3v5B8fCoqeNUMWywWMSqHVCNgktsGG4EthOFNAoEtoLR7cxvPaHSPJYPZpygH9GB5CFn1Fipft8rltyyOwdZJV5GSpCh1it+dfsxSyOUhgmqdcdzE+NPqDKcCZwWuqnGhLIRHWDHUkkj1P5kfuiUnFmlT8JY2ZKGzNXfExMaaT2OAtsZUTPUy95M/M/rpCa89idcJqlByRaLwlQQE5PZ16TPFTIjxpZQpri9lbAhVZQZm03BhuAtv7xKmpWyd1Gu1C9L1ZssjjycwCmcgwdXUIU7qEEDGCA8wyu8OY/Oi/PufCxac042cwx/4Hz+AK3vjNo=</latexit>
S
<
latexit
sha1_base64="vFchJGr6Z+gyWiveB04FdIL/myI=">AAAB6HicbVDLTgJBEOzFF+IL9ehlIjHxRHbRRI9ELx4hyiOBDZkdemFkdnYzM2tCCF/gxYPGePWTvPk3DrAHBSvppFLVne6uIBFcG9f9dnJr6xubW/ntws7u3v5B8fCoqeNUMWywWMSqHVCNgktsGG4EthOFNAoEtoLR7cxvPaHSPJYPZpygH9GB5CFn1Fipft8rltyyOwdZJV5GSpCh1it+dfsxSyOUhgmqdcdzE+NPqDKcCZwWuqnGhLIRHWDHUkkj1P5kfuiUnFmlT8JY2ZKGzNXfExMaaT2OAtsZUTPUy95M/M/rpCa89idcJqlByRaLwlQQE5PZ16TPFTIjxpZQpri9lbAhVZQZm03BhuAtv7xKmpWyd1Gu1C9L1ZssjjycwCmcgwdXUIU7qEEDGCA8wyu8OY/Oi/PufCxac042cwx/4Hz+AK9zjNs=</latexit>
R = S
<latexit
sha1_base64="nDUP4fccke/FNLKaaM8Wqz9O1M8=">AAAB6nicbVDLSgNBEOz1GeMr6tHLYBA8hd0o6EUIevEYjXlAsoTZSW8yZHZ2mZkVQsgnePGgiFe/yJt/4yTZgyYWNBRV3XR3BYng2rjut7Oyura+sZnbym/v7O7tFw4OGzpOFcM6i0WsWgHVKLjEuuFGYCtRSKNAYDMY3k795hMqzWP5aEYJ+hHtSx5yRo2Vag/XtW6h6JbcGcgy8TJShAzVbuGr04tZGqE0TFCt256bGH9MleFM4CTfSTUmlA1pH9uWShqh9sezUyfk1Co9EsbKljRkpv6eGNNI61EU2M6ImoFe9Kbif147NeGVP+YySQ1KNl8UpoKYmEz/Jj2ukBkxsoQyxe2thA2ooszYdPI2BG/x5WXSKJe881L5/qJYucniyMExnMAZeHAJFbiDKtSBQR+e4RXeHOG8OO/Ox7x1xclmjuAPnM8f0umNfg==</latexit>
K=M>2 K=5 ✏g
<latexit
sha1_base64="mglHXcqwu+eocCx6ul5cTySUvNg=">AAAB8XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae2oWy2k3bpZhN2N0IJ/RdePCji1X/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqGDZZLGLVCahGwSU2DTcCO4lCGgUC28H4dua3n1BpHssHM0nQj+hQ8pAzaqz02MNEcxHL/rBfrrhVdw6ySrycVCBHo1/+6g1ilkYoDRNU667nJsbPqDKcCZyWeqnGhLIxHWLXUkkj1H42v3hKzqwyIGGsbElD5urviYxGWk+iwHZG1Iz0sjcT//O6qQmv/YzLJDUo2WJRmApiYjJ7nwy4QmbExBLKFLe3EjaiijJjQyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAEBhKe4RXeHO28OO/Ox6K14OQzx/AHzucPyzeQ/g==</latexit>
↵
<
latexit
sha1_base64="+wSBPeL8nxBdvzPXA2qswhGhfpg=">AAAB7XicbVBNS8NAEJ3Ur1q/qh69LBbBU0mqoMeiF48V7Ae0oUy2m3btZhN2N0IJ/Q9ePCji1f/jzX/jts1BWx8MPN6bYWZekAiujet+O4W19Y3NreJ2aWd3b/+gfHjU0nGqKGvSWMSqE6BmgkvWNNwI1kkUwygQrB2Mb2d++4kpzWP5YCYJ8yMcSh5yisZKrR6KZIT9csWtunOQVeLlpAI5Gv3yV28Q0zRi0lCBWnc9NzF+hspwKti01Es1S5COcci6lkqMmPaz+bVTcmaVAQljZUsaMld/T2QYaT2JAtsZoRnpZW8m/ud1UxNe+xmXSWqYpItFYSqIicnsdTLgilEjJpYgVdzeSugIFVJjAyrZELzll1dJq1b1Lqq1+8tK/SaPowgncArn4MEV1OEOGtAECo/wDK/w5sTOi/PufCxaC04+cwx/4Hz+AIzPjxw=</latexit>
competing
states
separated by
energy barrier
continuous
specialization
transition
disccontinuous
transition
anti-spec.
12
Hidden unit Specialization in Layered Neural Networks:
ReLU vs. Sigmoidal Activation
Elisa Oostwal, Michiel Straat, M. Biehl
Physica A 564: 125517 (2021)
Phase Transitions in Soft-Committee Machines
M. Biehl, E. Schlösser, M. Ahr
Europhysics Letters 44: 261-267 (1998)
Statistical Physics and Practical Training of Soft-Committee Machines
M. Ahr, M. Biehl, R. Urbanczik
European Physics B 10: 583-588 (1999)
sigmoidal activation
high-T, arbitrary K = M
sigmoidal activation,
replica, large
T < ∞
K = M → ∞
ReLU activation
high-T, arbitrary K = M
references
13
challenges:
- more general activation functions,
see the following talk by Frederieke Richert
- overfitting/underfitting (mismatched students)
- low temperature training (Annealed Approximation, Replica)
outlook
13
challenges:
- more general activation functions,
see the following talk by Frederieke Richert
- overfitting/underfitting (mismatched students)
- low temperature training (Annealed Approximation, Replica)
- many layers (deep networks, tree architectures)
- realistic input densities
- material specific activation functions
- regularization techniques, e.g. drop-out
-
outlook
14
Cognigron March 2021 12 / 11
www.cs.rug.nl/~biehl m.biehl@rug.nl

More Related Content

Similar to stat-phys-appis-reduced.pdf

Harmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningHarmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningSungbin Lim
 
Reinforcement Learning: Hidden Theory and New Super-Fast Algorithms
Reinforcement Learning: Hidden Theory and New Super-Fast AlgorithmsReinforcement Learning: Hidden Theory and New Super-Fast Algorithms
Reinforcement Learning: Hidden Theory and New Super-Fast AlgorithmsSean Meyn
 
Data mining assignment 2
Data mining assignment 2Data mining assignment 2
Data mining assignment 2BarryK88
 
Zap Q-Learning - ISMP 2018
Zap Q-Learning - ISMP 2018Zap Q-Learning - ISMP 2018
Zap Q-Learning - ISMP 2018Sean Meyn
 
2D CFD Code Based on MATLAB- As Good As FLUENT!
2D CFD Code Based on MATLAB- As Good As FLUENT!2D CFD Code Based on MATLAB- As Good As FLUENT!
2D CFD Code Based on MATLAB- As Good As FLUENT!Jiannan Tan
 
A nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formulaA nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formulaAlexander Litvinenko
 
Algorithmic Thermodynamics
Algorithmic ThermodynamicsAlgorithmic Thermodynamics
Algorithmic ThermodynamicsSunny Kr
 
Convergence of ABC methods
Convergence of ABC methodsConvergence of ABC methods
Convergence of ABC methodsChristian Robert
 
Workshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael MartinWorkshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael MartinChristian Robert
 
Variational inference
Variational inference  Variational inference
Variational inference Natan Katz
 
Optimization of probabilistic argumentation with Markov processes
Optimization of probabilistic argumentation with Markov processesOptimization of probabilistic argumentation with Markov processes
Optimization of probabilistic argumentation with Markov processesEmmanuel Hadoux
 
Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013
Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013
Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013Christian Robert
 
Discussion cabras-robert-130323171455-phpapp02
Discussion cabras-robert-130323171455-phpapp02Discussion cabras-robert-130323171455-phpapp02
Discussion cabras-robert-130323171455-phpapp02Deb Roy
 
Atomic Scheduling of Appliance Energy Consumption in Residential Smart Grid
Atomic Scheduling of Appliance Energy Consumption in Residential Smart GridAtomic Scheduling of Appliance Energy Consumption in Residential Smart Grid
Atomic Scheduling of Appliance Energy Consumption in Residential Smart GridXi'an Jiaotong-Liverpool University
 
MarcoCeze_defense
MarcoCeze_defenseMarcoCeze_defense
MarcoCeze_defenseMarco Ceze
 
Curve fitting and Optimization
Curve fitting and OptimizationCurve fitting and Optimization
Curve fitting and OptimizationSyahrul Senin
 

Similar to stat-phys-appis-reduced.pdf (20)

Presentation OCIP 2015
Presentation OCIP 2015Presentation OCIP 2015
Presentation OCIP 2015
 
Bayesian computation with INLA
Bayesian computation with INLABayesian computation with INLA
Bayesian computation with INLA
 
Harmonic Analysis and Deep Learning
Harmonic Analysis and Deep LearningHarmonic Analysis and Deep Learning
Harmonic Analysis and Deep Learning
 
Reinforcement Learning: Hidden Theory and New Super-Fast Algorithms
Reinforcement Learning: Hidden Theory and New Super-Fast AlgorithmsReinforcement Learning: Hidden Theory and New Super-Fast Algorithms
Reinforcement Learning: Hidden Theory and New Super-Fast Algorithms
 
Data mining assignment 2
Data mining assignment 2Data mining assignment 2
Data mining assignment 2
 
Zap Q-Learning - ISMP 2018
Zap Q-Learning - ISMP 2018Zap Q-Learning - ISMP 2018
Zap Q-Learning - ISMP 2018
 
2D CFD Code Based on MATLAB- As Good As FLUENT!
2D CFD Code Based on MATLAB- As Good As FLUENT!2D CFD Code Based on MATLAB- As Good As FLUENT!
2D CFD Code Based on MATLAB- As Good As FLUENT!
 
A nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formulaA nonlinear approximation of the Bayesian Update formula
A nonlinear approximation of the Bayesian Update formula
 
Algorithmic Thermodynamics
Algorithmic ThermodynamicsAlgorithmic Thermodynamics
Algorithmic Thermodynamics
 
the ABC of ABC
the ABC of ABCthe ABC of ABC
the ABC of ABC
 
Convergence of ABC methods
Convergence of ABC methodsConvergence of ABC methods
Convergence of ABC methods
 
Workshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael MartinWorkshop in honour of Don Poskitt and Gael Martin
Workshop in honour of Don Poskitt and Gael Martin
 
Variational inference
Variational inference  Variational inference
Variational inference
 
Optimization of probabilistic argumentation with Markov processes
Optimization of probabilistic argumentation with Markov processesOptimization of probabilistic argumentation with Markov processes
Optimization of probabilistic argumentation with Markov processes
 
Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013
Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013
Discussion of ABC talk by Stefano Cabras, Padova, March 21, 2013
 
Discussion cabras-robert-130323171455-phpapp02
Discussion cabras-robert-130323171455-phpapp02Discussion cabras-robert-130323171455-phpapp02
Discussion cabras-robert-130323171455-phpapp02
 
Atomic Scheduling of Appliance Energy Consumption in Residential Smart Grid
Atomic Scheduling of Appliance Energy Consumption in Residential Smart GridAtomic Scheduling of Appliance Energy Consumption in Residential Smart Grid
Atomic Scheduling of Appliance Energy Consumption in Residential Smart Grid
 
MarcoCeze_defense
MarcoCeze_defenseMarcoCeze_defense
MarcoCeze_defense
 
Curve fitting and Optimization
Curve fitting and OptimizationCurve fitting and Optimization
Curve fitting and Optimization
 
PTSP PPT.pdf
PTSP PPT.pdfPTSP PPT.pdf
PTSP PPT.pdf
 

More from University of Groningen

Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024
Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024
Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024University of Groningen
 
Evidence for tissue and stage-specific composition of the ribosome: machine l...
Evidence for tissue and stage-specific composition of the ribosome: machine l...Evidence for tissue and stage-specific composition of the ribosome: machine l...
Evidence for tissue and stage-specific composition of the ribosome: machine l...University of Groningen
 
The statistical physics of learning revisted: Phase transitions in layered ne...
The statistical physics of learning revisted: Phase transitions in layered ne...The statistical physics of learning revisted: Phase transitions in layered ne...
The statistical physics of learning revisted: Phase transitions in layered ne...University of Groningen
 
Interpretable machine-learning (in endocrinology and beyond)
Interpretable machine-learning (in endocrinology and beyond)Interpretable machine-learning (in endocrinology and beyond)
Interpretable machine-learning (in endocrinology and beyond)University of Groningen
 
2020: Prototype-based classifiers and relevance learning: medical application...
2020: Prototype-based classifiers and relevance learning: medical application...2020: Prototype-based classifiers and relevance learning: medical application...
2020: Prototype-based classifiers and relevance learning: medical application...University of Groningen
 
2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...
2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...
2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...University of Groningen
 
2020: So you thought the ribosome was constant and conserved ...
2020: So you thought the ribosome was constant and conserved ... 2020: So you thought the ribosome was constant and conserved ...
2020: So you thought the ribosome was constant and conserved ... University of Groningen
 
Prototype-based classifiers and their applications in the life sciences
Prototype-based classifiers and their applications in the life sciencesPrototype-based classifiers and their applications in the life sciences
Prototype-based classifiers and their applications in the life sciencesUniversity of Groningen
 
Prototype-based models in machine learning
Prototype-based models in machine learningPrototype-based models in machine learning
Prototype-based models in machine learningUniversity of Groningen
 
The statistical physics of learning - revisited
The statistical physics of learning - revisitedThe statistical physics of learning - revisited
The statistical physics of learning - revisitedUniversity of Groningen
 
2013: Sometimes you can trust a rat - The sbv improver species translation ch...
2013: Sometimes you can trust a rat - The sbv improver species translation ch...2013: Sometimes you can trust a rat - The sbv improver species translation ch...
2013: Sometimes you can trust a rat - The sbv improver species translation ch...University of Groningen
 
2013: Prototype-based learning and adaptive distances for classification
2013: Prototype-based learning and adaptive distances for classification2013: Prototype-based learning and adaptive distances for classification
2013: Prototype-based learning and adaptive distances for classificationUniversity of Groningen
 
2015: Distance based classifiers: Basic concepts, recent developments and app...
2015: Distance based classifiers: Basic concepts, recent developments and app...2015: Distance based classifiers: Basic concepts, recent developments and app...
2015: Distance based classifiers: Basic concepts, recent developments and app...University of Groningen
 
2016: Classification of FDG-PET Brain Data
2016: Classification of FDG-PET Brain Data2016: Classification of FDG-PET Brain Data
2016: Classification of FDG-PET Brain DataUniversity of Groningen
 
2016: Predicting Recurrence in Clear Cell Renal Cell Carcinoma
2016: Predicting Recurrence in Clear Cell Renal Cell Carcinoma2016: Predicting Recurrence in Clear Cell Renal Cell Carcinoma
2016: Predicting Recurrence in Clear Cell Renal Cell CarcinomaUniversity of Groningen
 
2017: Prototype-based models in unsupervised and supervised machine learning
2017: Prototype-based models in unsupervised and supervised machine learning2017: Prototype-based models in unsupervised and supervised machine learning
2017: Prototype-based models in unsupervised and supervised machine learningUniversity of Groningen
 

More from University of Groningen (20)

Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024
Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024
Interpretable machine learning in endocrinology, M. Biehl, APPIS 2024
 
ESE-Eyes-2023.pdf
ESE-Eyes-2023.pdfESE-Eyes-2023.pdf
ESE-Eyes-2023.pdf
 
APPIS-FDGPET.pdf
APPIS-FDGPET.pdfAPPIS-FDGPET.pdf
APPIS-FDGPET.pdf
 
prototypes-AMALEA.pdf
prototypes-AMALEA.pdfprototypes-AMALEA.pdf
prototypes-AMALEA.pdf
 
Evidence for tissue and stage-specific composition of the ribosome: machine l...
Evidence for tissue and stage-specific composition of the ribosome: machine l...Evidence for tissue and stage-specific composition of the ribosome: machine l...
Evidence for tissue and stage-specific composition of the ribosome: machine l...
 
The statistical physics of learning revisted: Phase transitions in layered ne...
The statistical physics of learning revisted: Phase transitions in layered ne...The statistical physics of learning revisted: Phase transitions in layered ne...
The statistical physics of learning revisted: Phase transitions in layered ne...
 
Interpretable machine-learning (in endocrinology and beyond)
Interpretable machine-learning (in endocrinology and beyond)Interpretable machine-learning (in endocrinology and beyond)
Interpretable machine-learning (in endocrinology and beyond)
 
Biehl hanze-2021
Biehl hanze-2021Biehl hanze-2021
Biehl hanze-2021
 
2020: Prototype-based classifiers and relevance learning: medical application...
2020: Prototype-based classifiers and relevance learning: medical application...2020: Prototype-based classifiers and relevance learning: medical application...
2020: Prototype-based classifiers and relevance learning: medical application...
 
2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...
2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...
2020: Phase transitions in layered neural networks: ReLU vs. sigmoidal activa...
 
2020: So you thought the ribosome was constant and conserved ...
2020: So you thought the ribosome was constant and conserved ... 2020: So you thought the ribosome was constant and conserved ...
2020: So you thought the ribosome was constant and conserved ...
 
Prototype-based classifiers and their applications in the life sciences
Prototype-based classifiers and their applications in the life sciencesPrototype-based classifiers and their applications in the life sciences
Prototype-based classifiers and their applications in the life sciences
 
Prototype-based models in machine learning
Prototype-based models in machine learningPrototype-based models in machine learning
Prototype-based models in machine learning
 
The statistical physics of learning - revisited
The statistical physics of learning - revisitedThe statistical physics of learning - revisited
The statistical physics of learning - revisited
 
2013: Sometimes you can trust a rat - The sbv improver species translation ch...
2013: Sometimes you can trust a rat - The sbv improver species translation ch...2013: Sometimes you can trust a rat - The sbv improver species translation ch...
2013: Sometimes you can trust a rat - The sbv improver species translation ch...
 
2013: Prototype-based learning and adaptive distances for classification
2013: Prototype-based learning and adaptive distances for classification2013: Prototype-based learning and adaptive distances for classification
2013: Prototype-based learning and adaptive distances for classification
 
2015: Distance based classifiers: Basic concepts, recent developments and app...
2015: Distance based classifiers: Basic concepts, recent developments and app...2015: Distance based classifiers: Basic concepts, recent developments and app...
2015: Distance based classifiers: Basic concepts, recent developments and app...
 
2016: Classification of FDG-PET Brain Data
2016: Classification of FDG-PET Brain Data2016: Classification of FDG-PET Brain Data
2016: Classification of FDG-PET Brain Data
 
2016: Predicting Recurrence in Clear Cell Renal Cell Carcinoma
2016: Predicting Recurrence in Clear Cell Renal Cell Carcinoma2016: Predicting Recurrence in Clear Cell Renal Cell Carcinoma
2016: Predicting Recurrence in Clear Cell Renal Cell Carcinoma
 
2017: Prototype-based models in unsupervised and supervised machine learning
2017: Prototype-based models in unsupervised and supervised machine learning2017: Prototype-based models in unsupervised and supervised machine learning
2017: Prototype-based models in unsupervised and supervised machine learning
 

Recently uploaded

Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptxRajatChauhan518211
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCEPRINCE C P
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...ssifa0344
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksSérgio Sacani
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPirithiRaju
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bSérgio Sacani
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfSumit Kumar yadav
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Patrick Diehl
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...Sérgio Sacani
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Sérgio Sacani
 
A relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfA relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfnehabiju2046
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisDiwakar Mishra
 

Recently uploaded (20)

Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptx
 
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
Formation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disksFormation of low mass protostars and their circumstellar disks
Formation of low mass protostars and their circumstellar disks
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdfPests of cotton_Sucking_Pests_Dr.UPR.pdf
Pests of cotton_Sucking_Pests_Dr.UPR.pdf
 
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43bNightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
Nightside clouds and disequilibrium chemistry on the hot Jupiter WASP-43b
 
Botany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdfBotany 4th semester series (krishna).pdf
Botany 4th semester series (krishna).pdf
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
 
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
Discovery of an Accretion Streamer and a Slow Wide-angle Outflow around FUOri...
 
A relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfA relative description on Sonoporation.pdf
A relative description on Sonoporation.pdf
 
CELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdfCELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdf
 
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral AnalysisRaman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
Raman spectroscopy.pptx M Pharm, M Sc, Advanced Spectral Analysis
 

stat-phys-appis-reduced.pdf