SlideShare a Scribd company logo
1 of 2
Download to read offline
The detailed derivation of the derivatives in Table 2 of 
Marginalized Denoising Auto-encoders for Nonlinear Representations 
by M. Chen, K. Weinberger, F. Sha, and Y. Bengio 
Tomonari MASADA @ Nagasaki University 
October 14, 2014 
The derivative @zh 
@~xd 
can be obtained as follows: 
z =  
( 
W~x + b 
) 
= 
1 
1 + exp(W~x  b) 
(1) 
) @zh 
@~xd 
= 
@ 
@~xd 
1 
1 + exp(Σ 
d whd~xd  bh) 
= 
whd exp(Σ 
d whd~xd  bh) 
f1 + exp(Σ 
d whd~xd  bh)g2 
= 
1 
1 + exp( 
Σ 
d whd~xd  bh) 
 
{ 
1  1 
1 + exp( 
Σ 
d whd~xd  bh) 
} 
 whd 
= zh(1  zh)whd : (2) 
For the cross-entropy loss, we obtain the following: 
( 
x; f(~x) 
ℓ 
) 
= x 
⊤ 
log (W 
⊤ 
z + b 
′ 
)  (1  x) 
⊤ 
log 
{ 
1  (W 
⊤ 
z + b 
} 
′ 
) 
= x 
⊤ 
log 
{ 
1 
1 + exp(W⊤z  b′) 
} 
 (1  x) 
⊤ 
log 
{ 
exp(W⊤z  b′) 
1 + exp(W⊤z  b′) 
} 
= x 
⊤ 
logf1 + exp(W 
⊤ 
z  b 
′ 
)g  (1  x) 
⊤ 
(W 
⊤ 
z  b 
′ 
) + (1  x) 
⊤ 
log 
{ 
1 + exp(W 
⊤ 
z  b 
} 
′ 
) 
⊤ 
(W 
= (1  x) 
⊤ 
z  b 
′ 
) + 1 
⊤ 
log 
{ 
1 + exp(W 
⊤ 
z  b 
′ 
) 
} 
=  
Σ 
d 
(1  xd) 
( 
 
Σ 
h 
′ 
d 
whdzh  b 
) 
+ 
Σ 
d 
log 
{ 
1 + exp 
( 
 
Σ 
h 
′ 
d 
whdzh  b 
)} 
(3) 
) @ℓ 
@zh 
= 
Σ 
d 
(1  xd)whd  
Σ 
d 
whd exp(Σ 
h whdzh  b′ 
d) 
1 + exp(Σ 
h whdzh  b′ 
d) 
(4) 
) @2ℓ 
@z2h 
=  @ 
@zh 
Σ 
d 
whd exp(Σ 
h whdzh  b′ 
d) 
1 + exp( 
Σ 
h whdzh  b′ 
d) 
= 
Σ 
d 
hd exp( 
w2 
Σ 
h whdzh  b′ 
d) 
1 + exp(Σ 
h whdzh  b′ 
d) 
 
Σ 
d 
w2 
hd 
fexp( 
Σ 
h whdzh  b′ 
d)g2 
f1 + exp(Σ 
h whdzh  b′ 
d)g2 
= 
Σ 
d 
hd exp(Σ 
w2 
h whdzh  b′ 
d) 
f1 + exp(Σ 
h whdzh  b′ 
d)g2 
= 
Σ 
d 
( 
1 
1 + exp(Σ 
h whdzh  b′ 
d) 
)( 
1  1 
1 + exp(Σ 
h whdzh  b′ 
d) 
) 
w2 
hd 
= 
Σ 
d 
yd(1  yd)w2 
hd : (5) 
1
For the squared loss, we obtain the following: 
( 
x; f(~x) 
ℓ 
) 
= ∥x  (W 
⊤ 
z + b 
′ 
)∥2 = 
Σ 
d 
{ 
xd  
(Σ 
h 
whdzh + b 
′ 
d 
)}2 
(6) 
) @ℓ 
@zh 
= 
@ 
@zh 
Σ 
d 
{ 
xd  
(Σ 
h 
whdzh + b 
′ 
d 
)}2 
= 2 
Σ 
d 
whd 
{ 
xd  
(Σ 
h 
′ 
d 
whdzh + b 
)} 
(7) 
) @2ℓ 
@z2h 
=  @ 
@zh 
2 
Σ 
d 
whd 
{ 
xd  
(Σ 
h 
′ 
d 
whdzh + b 
)} 
= 2 
Σ 
d 
w2 
hd : (8) 
2

More Related Content

What's hot

Christian Gill ''Functional programming for the people''
Christian Gill ''Functional programming for the people''Christian Gill ''Functional programming for the people''
Christian Gill ''Functional programming for the people''OdessaJS Conf
 
Monads from Definition
Monads from DefinitionMonads from Definition
Monads from DefinitionDierk König
 
Lista Plantão 03 - 7º ano
Lista Plantão 03 - 7º anoLista Plantão 03 - 7º ano
Lista Plantão 03 - 7º anoProf. Materaldo
 
Ejercicios radhames ultima unidad
Ejercicios radhames ultima unidadEjercicios radhames ultima unidad
Ejercicios radhames ultima unidadyusmelycardoza
 
Statistics formulaee
Statistics formulaeeStatistics formulaee
Statistics formulaeeSumit Satam
 
A gentle introduction to functional programming through music and clojure
A gentle introduction to functional programming through music and clojureA gentle introduction to functional programming through music and clojure
A gentle introduction to functional programming through music and clojurePaul Lam
 
imager package in R and examples..
imager package in R and examples..imager package in R and examples..
imager package in R and examples..Dr. Volkan OBAN
 
Factoring Trinomials
Factoring TrinomialsFactoring Trinomials
Factoring Trinomialsguest7370dc
 

What's hot (18)

Christian Gill ''Functional programming for the people''
Christian Gill ''Functional programming for the people''Christian Gill ''Functional programming for the people''
Christian Gill ''Functional programming for the people''
 
Guia 1
Guia 1Guia 1
Guia 1
 
Monads from Definition
Monads from DefinitionMonads from Definition
Monads from Definition
 
Invers fungsi
Invers fungsiInvers fungsi
Invers fungsi
 
Lista Plantão 03 - 7º ano
Lista Plantão 03 - 7º anoLista Plantão 03 - 7º ano
Lista Plantão 03 - 7º ano
 
Maths ms
Maths msMaths ms
Maths ms
 
Ejercicios radhames ultima unidad
Ejercicios radhames ultima unidadEjercicios radhames ultima unidad
Ejercicios radhames ultima unidad
 
Statistics formulaee
Statistics formulaeeStatistics formulaee
Statistics formulaee
 
Al.ex2
Al.ex2Al.ex2
Al.ex2
 
Al.ex1
Al.ex1Al.ex1
Al.ex1
 
A gentle introduction to functional programming through music and clojure
A gentle introduction to functional programming through music and clojureA gentle introduction to functional programming through music and clojure
A gentle introduction to functional programming through music and clojure
 
Ch02 22
Ch02 22Ch02 22
Ch02 22
 
imager package in R and examples..
imager package in R and examples..imager package in R and examples..
imager package in R and examples..
 
Natalia rosales duban erazo
Natalia rosales duban erazoNatalia rosales duban erazo
Natalia rosales duban erazo
 
Lagrange
LagrangeLagrange
Lagrange
 
1.funtions (1)
1.funtions (1)1.funtions (1)
1.funtions (1)
 
133467 p3a2
133467 p3a2133467 p3a2
133467 p3a2
 
Factoring Trinomials
Factoring TrinomialsFactoring Trinomials
Factoring Trinomials
 

Viewers also liked

A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...
A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...
A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...Tomonari Masada
 
Word count in Husserliana Volumes 1 to 28
Word count in Husserliana Volumes 1 to 28Word count in Husserliana Volumes 1 to 28
Word count in Husserliana Volumes 1 to 28Tomonari Masada
 
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet AllocationA Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet AllocationTomonari Masada
 
A Note on PCVB0 for HDP-LDA
A Note on PCVB0 for HDP-LDAA Note on PCVB0 for HDP-LDA
A Note on PCVB0 for HDP-LDATomonari Masada
 
ChronoSAGE: Diversifying Topic Modeling Chronologically
ChronoSAGE: Diversifying Topic Modeling ChronologicallyChronoSAGE: Diversifying Topic Modeling Chronologically
ChronoSAGE: Diversifying Topic Modeling ChronologicallyTomonari Masada
 
Supplementary material for my following paper: Infinite Latent Process Decomp...
Supplementary material for my following paper: Infinite Latent Process Decomp...Supplementary material for my following paper: Infinite Latent Process Decomp...
Supplementary material for my following paper: Infinite Latent Process Decomp...Tomonari Masada
 
Semi-supervised Bibliographic Element Segmentation with Latent Permutations
Semi-supervised Bibliographic Element Segmentation with Latent PermutationsSemi-supervised Bibliographic Element Segmentation with Latent Permutations
Semi-supervised Bibliographic Element Segmentation with Latent PermutationsTomonari Masada
 
A Note on BPTT for LSTM LM
A Note on BPTT for LSTM LMA Note on BPTT for LSTM LM
A Note on BPTT for LSTM LMTomonari Masada
 
生成モデルの Deep Learning
生成モデルの Deep Learning生成モデルの Deep Learning
生成モデルの Deep LearningSeiya Tokui
 
猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoderSho Tatsuno
 

Viewers also liked (10)

A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...
A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...
A derivation of the sampling formulas for An Entity-Topic Model for Entity Li...
 
Word count in Husserliana Volumes 1 to 28
Word count in Husserliana Volumes 1 to 28Word count in Husserliana Volumes 1 to 28
Word count in Husserliana Volumes 1 to 28
 
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet AllocationA Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
 
A Note on PCVB0 for HDP-LDA
A Note on PCVB0 for HDP-LDAA Note on PCVB0 for HDP-LDA
A Note on PCVB0 for HDP-LDA
 
ChronoSAGE: Diversifying Topic Modeling Chronologically
ChronoSAGE: Diversifying Topic Modeling ChronologicallyChronoSAGE: Diversifying Topic Modeling Chronologically
ChronoSAGE: Diversifying Topic Modeling Chronologically
 
Supplementary material for my following paper: Infinite Latent Process Decomp...
Supplementary material for my following paper: Infinite Latent Process Decomp...Supplementary material for my following paper: Infinite Latent Process Decomp...
Supplementary material for my following paper: Infinite Latent Process Decomp...
 
Semi-supervised Bibliographic Element Segmentation with Latent Permutations
Semi-supervised Bibliographic Element Segmentation with Latent PermutationsSemi-supervised Bibliographic Element Segmentation with Latent Permutations
Semi-supervised Bibliographic Element Segmentation with Latent Permutations
 
A Note on BPTT for LSTM LM
A Note on BPTT for LSTM LMA Note on BPTT for LSTM LM
A Note on BPTT for LSTM LM
 
生成モデルの Deep Learning
生成モデルの Deep Learning生成モデルの Deep Learning
生成モデルの Deep Learning
 
猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder
 

Similar to The detailed derivation of the derivatives in Table 2 of Marginalized Denoising Auto-encoders for Nonlinear Representations by M. Chen, K. Weinberger, F. Sha, and Y. Bengio

lect4ggghjjjg t I c jifr7hvftu b gvvbb.pdf
lect4ggghjjjg t I c jifr7hvftu b gvvbb.pdflect4ggghjjjg t I c jifr7hvftu b gvvbb.pdf
lect4ggghjjjg t I c jifr7hvftu b gvvbb.pdfHebaEng
 
Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...
Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...
Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...Hareem Aslam
 
Iit jee question_paper
Iit jee question_paperIit jee question_paper
Iit jee question_paperRahulMishra774
 
Admissions in India 2015
Admissions in India 2015Admissions in India 2015
Admissions in India 2015Edhole.com
 
Communication systems solution manual 5th edition
Communication systems solution manual 5th editionCommunication systems solution manual 5th edition
Communication systems solution manual 5th editionTayeen Ahmed
 
comp diff
comp diffcomp diff
comp diffdianenz
 
Compfuncdiff
CompfuncdiffCompfuncdiff
Compfuncdiffdianenz
 
Sparse Representation of Multivariate Extremes with Applications to Anomaly R...
Sparse Representation of Multivariate Extremes with Applications to Anomaly R...Sparse Representation of Multivariate Extremes with Applications to Anomaly R...
Sparse Representation of Multivariate Extremes with Applications to Anomaly R...Hayato Watanabe
 
01 sets, relations and functions
01   sets, relations and functions01   sets, relations and functions
01 sets, relations and functionsvivieksunder
 
Gabarito completo anton_calculo_8ed_caps_01_08
Gabarito completo anton_calculo_8ed_caps_01_08Gabarito completo anton_calculo_8ed_caps_01_08
Gabarito completo anton_calculo_8ed_caps_01_08joseotaviosurdi
 
Day 5 examples u6w14
Day 5 examples u6w14Day 5 examples u6w14
Day 5 examples u6w14jchartiersjsd
 

Similar to The detailed derivation of the derivatives in Table 2 of Marginalized Denoising Auto-encoders for Nonlinear Representations by M. Chen, K. Weinberger, F. Sha, and Y. Bengio (20)

lect4ggghjjjg t I c jifr7hvftu b gvvbb.pdf
lect4ggghjjjg t I c jifr7hvftu b gvvbb.pdflect4ggghjjjg t I c jifr7hvftu b gvvbb.pdf
lect4ggghjjjg t I c jifr7hvftu b gvvbb.pdf
 
Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...
Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...
Solution Manual : Chapter - 07 Exponential, Logarithmic and Inverse Trigonome...
 
Integral table
Integral tableIntegral table
Integral table
 
Iit jee question_paper
Iit jee question_paperIit jee question_paper
Iit jee question_paper
 
Hw5sols
Hw5solsHw5sols
Hw5sols
 
Admissions in India 2015
Admissions in India 2015Admissions in India 2015
Admissions in India 2015
 
Tcu12 crc multi
Tcu12 crc multiTcu12 crc multi
Tcu12 crc multi
 
Communication systems solution manual 5th edition
Communication systems solution manual 5th editionCommunication systems solution manual 5th edition
Communication systems solution manual 5th edition
 
12th mcq
12th mcq12th mcq
12th mcq
 
12th mcq
12th mcq12th mcq
12th mcq
 
comp diff
comp diffcomp diff
comp diff
 
Compfuncdiff
CompfuncdiffCompfuncdiff
Compfuncdiff
 
Sparse Representation of Multivariate Extremes with Applications to Anomaly R...
Sparse Representation of Multivariate Extremes with Applications to Anomaly R...Sparse Representation of Multivariate Extremes with Applications to Anomaly R...
Sparse Representation of Multivariate Extremes with Applications to Anomaly R...
 
maths basics
maths basicsmaths basics
maths basics
 
Dif int
Dif intDif int
Dif int
 
maths
maths maths
maths
 
Dubey
DubeyDubey
Dubey
 
01 sets, relations and functions
01   sets, relations and functions01   sets, relations and functions
01 sets, relations and functions
 
Gabarito completo anton_calculo_8ed_caps_01_08
Gabarito completo anton_calculo_8ed_caps_01_08Gabarito completo anton_calculo_8ed_caps_01_08
Gabarito completo anton_calculo_8ed_caps_01_08
 
Day 5 examples u6w14
Day 5 examples u6w14Day 5 examples u6w14
Day 5 examples u6w14
 

More from Tomonari Masada

Learning Latent Space Energy Based Prior Modelの解説
Learning Latent Space Energy Based Prior Modelの解説Learning Latent Space Energy Based Prior Modelの解説
Learning Latent Space Energy Based Prior Modelの解説Tomonari Masada
 
Denoising Diffusion Probabilistic Modelsの重要な式の解説
Denoising Diffusion Probabilistic Modelsの重要な式の解説Denoising Diffusion Probabilistic Modelsの重要な式の解説
Denoising Diffusion Probabilistic Modelsの重要な式の解説Tomonari Masada
 
Context-dependent Token-wise Variational Autoencoder for Topic Modeling
Context-dependent Token-wise Variational Autoencoder for Topic ModelingContext-dependent Token-wise Variational Autoencoder for Topic Modeling
Context-dependent Token-wise Variational Autoencoder for Topic ModelingTomonari Masada
 
A note on the density of Gumbel-softmax
A note on the density of Gumbel-softmaxA note on the density of Gumbel-softmax
A note on the density of Gumbel-softmaxTomonari Masada
 
トピックモデルの基礎と応用
トピックモデルの基礎と応用トピックモデルの基礎と応用
トピックモデルの基礎と応用Tomonari Masada
 
Expectation propagation for latent Dirichlet allocation
Expectation propagation for latent Dirichlet allocationExpectation propagation for latent Dirichlet allocation
Expectation propagation for latent Dirichlet allocationTomonari Masada
 
Mini-batch Variational Inference for Time-Aware Topic Modeling
Mini-batch Variational Inference for Time-Aware Topic ModelingMini-batch Variational Inference for Time-Aware Topic Modeling
Mini-batch Variational Inference for Time-Aware Topic ModelingTomonari Masada
 
A note on variational inference for the univariate Gaussian
A note on variational inference for the univariate GaussianA note on variational inference for the univariate Gaussian
A note on variational inference for the univariate GaussianTomonari Masada
 
Document Modeling with Implicit Approximate Posterior Distributions
Document Modeling with Implicit Approximate Posterior DistributionsDocument Modeling with Implicit Approximate Posterior Distributions
Document Modeling with Implicit Approximate Posterior DistributionsTomonari Masada
 
LDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka Composition
LDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka CompositionLDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka Composition
LDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka CompositionTomonari Masada
 
A Note on Latent LSTM Allocation
A Note on Latent LSTM AllocationA Note on Latent LSTM Allocation
A Note on Latent LSTM AllocationTomonari Masada
 
Topic modeling with Poisson factorization (2)
Topic modeling with Poisson factorization (2)Topic modeling with Poisson factorization (2)
Topic modeling with Poisson factorization (2)Tomonari Masada
 
A Simple Stochastic Gradient Variational Bayes for the Correlated Topic Model
A Simple Stochastic Gradient Variational Bayes for the Correlated Topic ModelA Simple Stochastic Gradient Variational Bayes for the Correlated Topic Model
A Simple Stochastic Gradient Variational Bayes for the Correlated Topic ModelTomonari Masada
 
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet AllocationA Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet AllocationTomonari Masada
 
A Topic Model for Traffic Speed Data Analysis
A Topic Model for Traffic Speed Data AnalysisA Topic Model for Traffic Speed Data Analysis
A Topic Model for Traffic Speed Data AnalysisTomonari Masada
 
Nonparametric Factor Analysis with Beta Process Priors の式解説
Nonparametric Factor Analysis with Beta Process Priors の式解説Nonparametric Factor Analysis with Beta Process Priors の式解説
Nonparametric Factor Analysis with Beta Process Priors の式解説Tomonari Masada
 

More from Tomonari Masada (20)

Learning Latent Space Energy Based Prior Modelの解説
Learning Latent Space Energy Based Prior Modelの解説Learning Latent Space Energy Based Prior Modelの解説
Learning Latent Space Energy Based Prior Modelの解説
 
Denoising Diffusion Probabilistic Modelsの重要な式の解説
Denoising Diffusion Probabilistic Modelsの重要な式の解説Denoising Diffusion Probabilistic Modelsの重要な式の解説
Denoising Diffusion Probabilistic Modelsの重要な式の解説
 
Context-dependent Token-wise Variational Autoencoder for Topic Modeling
Context-dependent Token-wise Variational Autoencoder for Topic ModelingContext-dependent Token-wise Variational Autoencoder for Topic Modeling
Context-dependent Token-wise Variational Autoencoder for Topic Modeling
 
A note on the density of Gumbel-softmax
A note on the density of Gumbel-softmaxA note on the density of Gumbel-softmax
A note on the density of Gumbel-softmax
 
トピックモデルの基礎と応用
トピックモデルの基礎と応用トピックモデルの基礎と応用
トピックモデルの基礎と応用
 
Expectation propagation for latent Dirichlet allocation
Expectation propagation for latent Dirichlet allocationExpectation propagation for latent Dirichlet allocation
Expectation propagation for latent Dirichlet allocation
 
Mini-batch Variational Inference for Time-Aware Topic Modeling
Mini-batch Variational Inference for Time-Aware Topic ModelingMini-batch Variational Inference for Time-Aware Topic Modeling
Mini-batch Variational Inference for Time-Aware Topic Modeling
 
A note on variational inference for the univariate Gaussian
A note on variational inference for the univariate GaussianA note on variational inference for the univariate Gaussian
A note on variational inference for the univariate Gaussian
 
Document Modeling with Implicit Approximate Posterior Distributions
Document Modeling with Implicit Approximate Posterior DistributionsDocument Modeling with Implicit Approximate Posterior Distributions
Document Modeling with Implicit Approximate Posterior Distributions
 
LDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka Composition
LDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka CompositionLDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka Composition
LDA-Based Scoring of Sequences Generated by RNN for Automatic Tanka Composition
 
A Note on ZINB-VAE
A Note on ZINB-VAEA Note on ZINB-VAE
A Note on ZINB-VAE
 
A Note on Latent LSTM Allocation
A Note on Latent LSTM AllocationA Note on Latent LSTM Allocation
A Note on Latent LSTM Allocation
 
A Note on TopicRNN
A Note on TopicRNNA Note on TopicRNN
A Note on TopicRNN
 
Topic modeling with Poisson factorization (2)
Topic modeling with Poisson factorization (2)Topic modeling with Poisson factorization (2)
Topic modeling with Poisson factorization (2)
 
Poisson factorization
Poisson factorizationPoisson factorization
Poisson factorization
 
A Simple Stochastic Gradient Variational Bayes for the Correlated Topic Model
A Simple Stochastic Gradient Variational Bayes for the Correlated Topic ModelA Simple Stochastic Gradient Variational Bayes for the Correlated Topic Model
A Simple Stochastic Gradient Variational Bayes for the Correlated Topic Model
 
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet AllocationA Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
A Simple Stochastic Gradient Variational Bayes for Latent Dirichlet Allocation
 
FDSE2015
FDSE2015FDSE2015
FDSE2015
 
A Topic Model for Traffic Speed Data Analysis
A Topic Model for Traffic Speed Data AnalysisA Topic Model for Traffic Speed Data Analysis
A Topic Model for Traffic Speed Data Analysis
 
Nonparametric Factor Analysis with Beta Process Priors の式解説
Nonparametric Factor Analysis with Beta Process Priors の式解説Nonparametric Factor Analysis with Beta Process Priors の式解説
Nonparametric Factor Analysis with Beta Process Priors の式解説
 

Recently uploaded

Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayEpec Engineered Technologies
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueBhangaleSonal
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxJuliansyahHarahap1
 
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Call Girls Mumbai
 
Introduction to Serverless with AWS Lambda
Introduction to Serverless with AWS LambdaIntroduction to Serverless with AWS Lambda
Introduction to Serverless with AWS LambdaOmar Fathy
 
School management system project Report.pdf
School management system project Report.pdfSchool management system project Report.pdf
School management system project Report.pdfKamal Acharya
 
kiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadkiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadhamedmustafa094
 
PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiesPE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiessarkmank1
 
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...drmkjayanthikannan
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdfAldoGarca30
 
Hostel management system project report..pdf
Hostel management system project report..pdfHostel management system project report..pdf
Hostel management system project report..pdfKamal Acharya
 
Moment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilMoment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilVinayVitekari
 
Computer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersComputer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersMairaAshraf6
 
Online electricity billing project report..pdf
Online electricity billing project report..pdfOnline electricity billing project report..pdf
Online electricity billing project report..pdfKamal Acharya
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapRishantSharmaFr
 
Verification of thevenin's theorem for BEEE Lab (1).pptx
Verification of thevenin's theorem for BEEE Lab (1).pptxVerification of thevenin's theorem for BEEE Lab (1).pptx
Verification of thevenin's theorem for BEEE Lab (1).pptxchumtiyababu
 
DC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equationDC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equationBhangaleSonal
 
DeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakesDeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakesMayuraD1
 

Recently uploaded (20)

FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
Standard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power PlayStandard vs Custom Battery Packs - Decoding the Power Play
Standard vs Custom Battery Packs - Decoding the Power Play
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptx
 
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
Bhubaneswar🌹Call Girls Bhubaneswar ❤Komal 9777949614 💟 Full Trusted CALL GIRL...
 
Introduction to Serverless with AWS Lambda
Introduction to Serverless with AWS LambdaIntroduction to Serverless with AWS Lambda
Introduction to Serverless with AWS Lambda
 
School management system project Report.pdf
School management system project Report.pdfSchool management system project Report.pdf
School management system project Report.pdf
 
kiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadkiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal load
 
PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiesPE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and properties
 
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
 
Hostel management system project report..pdf
Hostel management system project report..pdfHostel management system project report..pdf
Hostel management system project report..pdf
 
Moment Distribution Method For Btech Civil
Moment Distribution Method For Btech CivilMoment Distribution Method For Btech Civil
Moment Distribution Method For Btech Civil
 
Computer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersComputer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to Computers
 
Online electricity billing project report..pdf
Online electricity billing project report..pdfOnline electricity billing project report..pdf
Online electricity billing project report..pdf
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leap
 
Verification of thevenin's theorem for BEEE Lab (1).pptx
Verification of thevenin's theorem for BEEE Lab (1).pptxVerification of thevenin's theorem for BEEE Lab (1).pptx
Verification of thevenin's theorem for BEEE Lab (1).pptx
 
DC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equationDC MACHINE-Motoring and generation, Armature circuit equation
DC MACHINE-Motoring and generation, Armature circuit equation
 
DeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakesDeepFakes presentation : brief idea of DeepFakes
DeepFakes presentation : brief idea of DeepFakes
 
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
 

The detailed derivation of the derivatives in Table 2 of Marginalized Denoising Auto-encoders for Nonlinear Representations by M. Chen, K. Weinberger, F. Sha, and Y. Bengio

  • 1. The detailed derivation of the derivatives in Table 2 of Marginalized Denoising Auto-encoders for Nonlinear Representations by M. Chen, K. Weinberger, F. Sha, and Y. Bengio Tomonari MASADA @ Nagasaki University October 14, 2014 The derivative @zh @~xd can be obtained as follows: z = ( W~x + b ) = 1 1 + exp(W~x b) (1) ) @zh @~xd = @ @~xd 1 1 + exp(Σ d whd~xd bh) = whd exp(Σ d whd~xd bh) f1 + exp(Σ d whd~xd bh)g2 = 1 1 + exp( Σ d whd~xd bh) { 1 1 1 + exp( Σ d whd~xd bh) } whd = zh(1 zh)whd : (2) For the cross-entropy loss, we obtain the following: ( x; f(~x) ℓ ) = x ⊤ log (W ⊤ z + b ′ ) (1 x) ⊤ log { 1 (W ⊤ z + b } ′ ) = x ⊤ log { 1 1 + exp(W⊤z b′) } (1 x) ⊤ log { exp(W⊤z b′) 1 + exp(W⊤z b′) } = x ⊤ logf1 + exp(W ⊤ z b ′ )g (1 x) ⊤ (W ⊤ z b ′ ) + (1 x) ⊤ log { 1 + exp(W ⊤ z b } ′ ) ⊤ (W = (1 x) ⊤ z b ′ ) + 1 ⊤ log { 1 + exp(W ⊤ z b ′ ) } = Σ d (1 xd) ( Σ h ′ d whdzh b ) + Σ d log { 1 + exp ( Σ h ′ d whdzh b )} (3) ) @ℓ @zh = Σ d (1 xd)whd Σ d whd exp(Σ h whdzh b′ d) 1 + exp(Σ h whdzh b′ d) (4) ) @2ℓ @z2h = @ @zh Σ d whd exp(Σ h whdzh b′ d) 1 + exp( Σ h whdzh b′ d) = Σ d hd exp( w2 Σ h whdzh b′ d) 1 + exp(Σ h whdzh b′ d) Σ d w2 hd fexp( Σ h whdzh b′ d)g2 f1 + exp(Σ h whdzh b′ d)g2 = Σ d hd exp(Σ w2 h whdzh b′ d) f1 + exp(Σ h whdzh b′ d)g2 = Σ d ( 1 1 + exp(Σ h whdzh b′ d) )( 1 1 1 + exp(Σ h whdzh b′ d) ) w2 hd = Σ d yd(1 yd)w2 hd : (5) 1
  • 2. For the squared loss, we obtain the following: ( x; f(~x) ℓ ) = ∥x (W ⊤ z + b ′ )∥2 = Σ d { xd (Σ h whdzh + b ′ d )}2 (6) ) @ℓ @zh = @ @zh Σ d { xd (Σ h whdzh + b ′ d )}2 = 2 Σ d whd { xd (Σ h ′ d whdzh + b )} (7) ) @2ℓ @z2h = @ @zh 2 Σ d whd { xd (Σ h ′ d whdzh + b )} = 2 Σ d w2 hd : (8) 2