SlideShare uma empresa Scribd logo
1 de 30
Baixar para ler offline
Backpropagation Derivation in Convolutional Neural
Networks
Punnoose A K
punnoose07@gmail.com
August 10, 2020
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 1 / 30
Contents
1 A simple CNN
2 Differential for various functions
3 Update equations for various CNN parameters
4 General order of update
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 2 / 30
A simple 2 Layered, Depth 1 CNN
X
K J1
f
C1
S1
G J2
f
C2
S2
A
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 3 / 30
Notations
1 X : Input feature. Assuming only 1 feature stream
2 K : Kernel. Depth 1
3 f : Rectified Linear Unit
4 C1 : First Convolution Output before ReLU
5 J1 : First Convolution Output after ReLU
6 S1 : Max Pooled Output, first layer
7 G : Kernel at second layer
8 C2 :Second Convolution Output before ReLU
9 J2 : Second Convolution Output after ReLU
10 S2 : Max Pooled Output, second layer
11 A : Flattened S2. I is the input size. A1 to AI
12 uij : weight between input and hidden layer
13 vjk: weight between hidden and output layer
14 yj : net input to hidden layer node j
15 zj : net input to output layer node j
16 bj : output of hidden layer node j
17 cj : output of output layer node j
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 4 / 30
What is to be learned here?
1 uij for 1 ≤ i ≤ I, 1 ≤ j ≤ H
2 vjk for 1 ≤ j ≤ H, 1 ≤ k ≤ O
3 Kernel G
4 Kernel K
Ignore the bias for time being
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 5 / 30
CNN Operations
1 C1=relu(Convolution(X,K))
2 S1=MaxPooling(C1)
3 C2=relu(Convolution(S1,G))
4 S2=MaxPooling(C2)
5 A=flatten(S2)
6 Feed A as the input to the fully connected network
7 sigmoid function at hidden layer
8 softmax function at output layer
9 Cross entropy as the loss function
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 6 / 30
Differential of Sigmoid Function
Let f (x) =
1
1 + e−x
f (x) =
e−x
(1 + e−x )2
=
1
1 + e−x
e−x
1 + e−x
=
1
1 + e−x
(1 −
1
1 + e−x
)
=f (x)(1 − f (x))
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 7 / 30
Differential of Softmax Function
Softmax function is defined as
fi = f (i; c1, c2...cO) =
eci
i eci
For finding the differential, there are 2 cases.
i.e, dfi
dck
where i = k
and dfi
dck
, where i = k.
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 8 / 30
Differential of Softmax Function
For sake of simplicity consider 2 class output, i.e, O = 2.
f1 = f (1; c1, c2) =
ec1
ec1 + ec2
Case: i = k
df1
dc1
=
(ec1 + ec2 )ec1 − ec1 ec1
(ec1 + ec2 )2
=
(ec1 + ec2 )ec1
(ec1 + ec2 )2
−
ec1 ec1
(ec1 + ec2 )2
=
ec1
(ec1 + ec2 )
−
ec1
(ec1 + ec2 )
2
=
ec1
(ec1 + ec2 )
1 −
ec1
(ec1 + ec2 )
=f1(1 − f1)
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 9 / 30
Differential of Softmax Function
Case: i = k
df1
dc2
= −
ec1 ec2
(ec1 + es2 )2
= −
ec1
(ec1 + es2 )
ec2
(ec1 + es2 )
= − f1f2
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 10 / 30
Differential of Softmax Function
Generalizing,
dfi
dck
=
fi (1 − fi ) i = k
−fi fk i = k
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 11 / 30
Differential of Cross Entropy Loss
Cross entropy loss between the output vector y and the target vector t of
size O is given by
L(y, t) = −
O
i
yi log(ti )
dL
dyi
= −
yi
ti
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 12 / 30
Differential of Rectified Linear Unit (ReLU)
ReLU is defined as
f (x) =max(0, x)
df
dx
=
1 x > 0
0 otherwise
In practise leaky ReLU is used, which is defined as
f (x) =max(c0, x)
df
dx
=
1 x > 0
c otherwise
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 13 / 30
Differential of Max Pooling
f (10, 20, 30, 40) = 40
Now if we increase 10 to 10.1, still f (10.1, 20, 30, 40) = 40
If we increase 30 to 30.1, still f (10.1, 20, 30, 40) = 40
Now if we increase 40 to 40.1, f (10.1, 20, 30, 40) = 40.1
if we increase 40 to 50, f (10.1, 20, 30, 50) = 50
The definition of differential is f (x) = limh→0
f (x+h)−f (x)
h
For the above function, the output changes linearly with the input(max).
So f (a, b, c, d) = 1
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 14 / 30
Backpropagation at Hidden to Output Layer
Input: X
Output: c
Target : t
z c
The output layer is divided into 2 sublayers shown in green and red. z is
the weighted sum and is passed to all the output nodes. The layer in red
actually performs the softmax operation and the softmax output is c.
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 15 / 30
Derivation
dL
dvjk
=
dL
dzk
dzk
dvjk
dL
dzk
=
O
o=1
dL
dco
dco
dzk
=
dL
dck
dck
dzk
+
o=k
dL
dco
dco
dzk
= −
tk
ck
ck(1 − ck) +
o=k
−to
co
(−cock)
= − tk(1 − ck) +
o=k
tock
= − tk + tkck +
o=k
tock
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 16 / 30
Derivation Continued
= −tk +
o=k
tock + tkck
= −tk +
o
tock
= −tk + ck
o
to
= −tk + ck1
dL
dzk
= ck − tk
dzk
dvjk
=bj
dL
dvjk
=(ck − tk)bj
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 17 / 30
Backpropagation at Input to Hidden Layer
dL
duij
=
k=O
k
dL
dzk
dzk
dbj
dbj
dyj
dyj
duij
=
dbj
dyj
dyj
duij
k
dL
dzk
dzk
dbj
= bj (1 − bj )xi
k
(ck − tk)vjk
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 18 / 30
Backpropagation for the kernels
X
K J1
f
C1
S1
G J2
f
C2
S2
A
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 19 / 30
Backpropagation for kernel G
We need to find dL
dG and dL
dK
dL
dG
=
dL
dA
dA
dS2
dS2
dC2
dC2
dJ2
dJ2
dG
As A = S2 flattened,
dL
dG
=
dL
dS2
dS2
dC2
dC2
dJ2
dJ2
dG
S2 is a max pooled version of C2. Operation wise, it is effectively selecting
the max value out of a set of numbers. Change in non max value in the
input set does not affect the output. A small change in max value value in
the input set affect linearly in the output. So it can be said that maximum
value out of a set, is locally linear. So dS2
dC2
= 1.
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 20 / 30
Backpropagation for kernel G
dL
dG
=
dL
dS2
dC2
dJ2
dJ2
dG
=
dL
dJ2
dJ2
dG
dL
dS2
is dL
dA written in square form.
dL
dAi
=
j k
dL
dzk
dzk
dbj
dbj
dyj
dyj
dAi
=
j k
(ck − tk)vjkbj (1 − bj )uij
dL
dA
=





dL
dA1
dL
dA2
...
dL
dAI





Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 21 / 30
Backpropagation for kernel G
dL
dS2
is dL
dA written in square form.
dL
dS2
=


dL
dA1
. .
. . .
. . dL
dAI


dC2
dJ2
=
1 x > 0
c otherwise
dL
dG
=
dL
dJ2
dJ2
dG
=conv(
dL
dJ2
, S1)
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 22 / 30
Backpropagation for the kernels
X
K J1
f
C1
S1
G J2
f
C2
S2
A
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 23 / 30
Backpropagation for kernel K
dL
dK
= conv(X,
dL
dJ1
)
We need to find dL
dJ1
.
dL
dJ1
=
dL
dS1
dS1
dC1
dC1
dJ1
dC1
dJ1
=
1 x > 0
c otherwise
dS1
dC1
=1
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 24 / 30
Backpropagation for kernel K
dL
dS1
=
dJ2
dG
Define G =1800
rotated G
Then,
dL
dS1
=fullconv(G ,
dL
dJ2
)
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 25 / 30
Full convolution explained
G11G12
G21G22 1800 rotate to
G22G21
G12G11
The convolution output is given as J2 =
J211 J212
J221 J222
The input matrix can be written as S1=
S131 S132 S133
S121 S122 S123
S111 S112 S113
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 26 / 30
Full convolution continued
where,
S111 =G11
dL
dJ211
S112 =G12
dL
dJ211
+ G11
dL
dJ212
S113 =G12
dL
dJ212
S121 =G21
dL
dJ211
+ G11
dL
dJ221
S122 =G22
dL
dJ211
+ G21
dL
dJ212
+ G12
dL
dJ221
+ G11
dL
dJ222
S123 =G22
dL
dJ212
+ G12
dL
dJ222
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 27 / 30
Full convolution continued
S131 =G21
dL
dJ221
S132 =G22
dL
dJ221
+ G21
dL
dJ222
S133 =G22
dL
dJ222
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 28 / 30
Order of update
1 Update hidden to output weights
2 Update input to hidden weights
3 Update kernel G
4 Update kernel K
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 29 / 30
Queries??
Connect me at punnoose07@gmail.com
Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 30 / 30

Mais conteúdo relacionado

Mais procurados

Graph Convolutional Neural Networks
Graph Convolutional Neural Networks Graph Convolutional Neural Networks
Graph Convolutional Neural Networks 신동 강
 
Computer Vision – From traditional approaches to deep neural networks
Computer Vision – From traditional approaches to deep neural networksComputer Vision – From traditional approaches to deep neural networks
Computer Vision – From traditional approaches to deep neural networksinovex GmbH
 
Unsupervised learning represenation with DCGAN
Unsupervised learning represenation with DCGANUnsupervised learning represenation with DCGAN
Unsupervised learning represenation with DCGANShyam Krishna Khadka
 
[1312.5602] Playing Atari with Deep Reinforcement Learning
[1312.5602] Playing Atari with Deep Reinforcement Learning[1312.5602] Playing Atari with Deep Reinforcement Learning
[1312.5602] Playing Atari with Deep Reinforcement LearningSeung Jae Lee
 
Introduction to CUDA
Introduction to CUDAIntroduction to CUDA
Introduction to CUDARaymond Tay
 
CNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesCNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesDmytro Mishkin
 
Comparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksComparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksVincenzo Lomonaco
 
Nvidia (History, GPU Architecture and New Pascal Architecture)
Nvidia (History, GPU Architecture and New Pascal Architecture)Nvidia (History, GPU Architecture and New Pascal Architecture)
Nvidia (History, GPU Architecture and New Pascal Architecture)Saksham Tanwar
 
graphics processing unit ppt
graphics processing unit pptgraphics processing unit ppt
graphics processing unit pptNitesh Dubey
 
Deep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageDeep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageWei Yang
 
Siggraph2016 - The Devil is in the Details: idTech 666
Siggraph2016 - The Devil is in the Details: idTech 666Siggraph2016 - The Devil is in the Details: idTech 666
Siggraph2016 - The Devil is in the Details: idTech 666Tiago Sousa
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsJinwon Lee
 
Look Ma, No Jutter! Optimizing Performance Across Oculus Mobile
Look Ma, No Jutter! Optimizing Performance Across Oculus MobileLook Ma, No Jutter! Optimizing Performance Across Oculus Mobile
Look Ma, No Jutter! Optimizing Performance Across Oculus MobileUnity Technologies
 
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)Fellowship at Vodafone FutureLab
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and ApplicationsEmanuele Ghelfi
 
Calculus in Machine Learning
Calculus in Machine Learning Calculus in Machine Learning
Calculus in Machine Learning Gokul Jayan
 
Graph Neural Network - Introduction
Graph Neural Network - IntroductionGraph Neural Network - Introduction
Graph Neural Network - IntroductionJungwon Kim
 

Mais procurados (20)

Graph Convolutional Neural Networks
Graph Convolutional Neural Networks Graph Convolutional Neural Networks
Graph Convolutional Neural Networks
 
Wasserstein GAN
Wasserstein GANWasserstein GAN
Wasserstein GAN
 
Computer Vision – From traditional approaches to deep neural networks
Computer Vision – From traditional approaches to deep neural networksComputer Vision – From traditional approaches to deep neural networks
Computer Vision – From traditional approaches to deep neural networks
 
Unsupervised learning represenation with DCGAN
Unsupervised learning represenation with DCGANUnsupervised learning represenation with DCGAN
Unsupervised learning represenation with DCGAN
 
AlexNet
AlexNetAlexNet
AlexNet
 
[1312.5602] Playing Atari with Deep Reinforcement Learning
[1312.5602] Playing Atari with Deep Reinforcement Learning[1312.5602] Playing Atari with Deep Reinforcement Learning
[1312.5602] Playing Atari with Deep Reinforcement Learning
 
Introduction to CUDA
Introduction to CUDAIntroduction to CUDA
Introduction to CUDA
 
CNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent AdvancesCNNs: from the Basics to Recent Advances
CNNs: from the Basics to Recent Advances
 
Comparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural NetworksComparing Incremental Learning Strategies for Convolutional Neural Networks
Comparing Incremental Learning Strategies for Convolutional Neural Networks
 
Nvidia (History, GPU Architecture and New Pascal Architecture)
Nvidia (History, GPU Architecture and New Pascal Architecture)Nvidia (History, GPU Architecture and New Pascal Architecture)
Nvidia (History, GPU Architecture and New Pascal Architecture)
 
graphics processing unit ppt
graphics processing unit pptgraphics processing unit ppt
graphics processing unit ppt
 
Deep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single imageDeep convolutional neural fields for depth estimation from a single image
Deep convolutional neural fields for depth estimation from a single image
 
Siggraph2016 - The Devil is in the Details: idTech 666
Siggraph2016 - The Devil is in the Details: idTech 666Siggraph2016 - The Devil is in the Details: idTech 666
Siggraph2016 - The Devil is in the Details: idTech 666
 
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual RepresentationsPR-231: A Simple Framework for Contrastive Learning of Visual Representations
PR-231: A Simple Framework for Contrastive Learning of Visual Representations
 
Look Ma, No Jutter! Optimizing Performance Across Oculus Mobile
Look Ma, No Jutter! Optimizing Performance Across Oculus MobileLook Ma, No Jutter! Optimizing Performance Across Oculus Mobile
Look Ma, No Jutter! Optimizing Performance Across Oculus Mobile
 
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
AlexNet(ImageNet Classification with Deep Convolutional Neural Networks)
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
Calculus in Machine Learning
Calculus in Machine Learning Calculus in Machine Learning
Calculus in Machine Learning
 
Graph Neural Network - Introduction
Graph Neural Network - IntroductionGraph Neural Network - Introduction
Graph Neural Network - Introduction
 
Decision tree learning
Decision tree learningDecision tree learning
Decision tree learning
 

Semelhante a Cnn backpropagation derivation

Convolutional neural network backpropagation derivation
Convolutional neural network backpropagation derivationConvolutional neural network backpropagation derivation
Convolutional neural network backpropagation derivationPunnoose A.K
 
A non-stiff boundary integral method for internal waves
A non-stiff boundary integral method for internal wavesA non-stiff boundary integral method for internal waves
A non-stiff boundary integral method for internal wavesAlex (Oleksiy) Varfolomiyev
 
Appendix of heterogeneous cellular network user distribution model
Appendix of heterogeneous cellular network user distribution modelAppendix of heterogeneous cellular network user distribution model
Appendix of heterogeneous cellular network user distribution modelCora Li
 
The reversible residual network
The reversible residual networkThe reversible residual network
The reversible residual networkThyrixYang1
 
Gate ee 2012 with solutions
Gate ee 2012 with solutionsGate ee 2012 with solutions
Gate ee 2012 with solutionskhemraj298
 
Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...
Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...
Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...Patrick Diehl
 
Gate ee 2003 with solutions
Gate ee 2003 with solutionsGate ee 2003 with solutions
Gate ee 2003 with solutionskhemraj298
 
20130912_mit _geordie_rose
20130912_mit _geordie_rose20130912_mit _geordie_rose
20130912_mit _geordie_roseGeordie Rose
 
Forward secure asynchronous messaging from puncturable encryption
Forward secure asynchronous messaging from puncturable encryptionForward secure asynchronous messaging from puncturable encryption
Forward secure asynchronous messaging from puncturable encryptionNational Chengchi University
 
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy AnnotationsToru Tamaki
 
Digit recognizer by convolutional neural network
Digit recognizer by convolutional neural networkDigit recognizer by convolutional neural network
Digit recognizer by convolutional neural networkDing Li
 
Magical float repr
Magical float reprMagical float repr
Magical float reprdickinsm
 
Quantum logic synthesis (srikanth)
Quantum logic synthesis (srikanth)Quantum logic synthesis (srikanth)
Quantum logic synthesis (srikanth)bitra11
 
Continuum Modeling and Control of Large Nonuniform Networks
Continuum Modeling and Control of Large Nonuniform NetworksContinuum Modeling and Control of Large Nonuniform Networks
Continuum Modeling and Control of Large Nonuniform NetworksYang Zhang
 

Semelhante a Cnn backpropagation derivation (20)

Convolutional neural network backpropagation derivation
Convolutional neural network backpropagation derivationConvolutional neural network backpropagation derivation
Convolutional neural network backpropagation derivation
 
A non-stiff boundary integral method for internal waves
A non-stiff boundary integral method for internal wavesA non-stiff boundary integral method for internal waves
A non-stiff boundary integral method for internal waves
 
Appendix of heterogeneous cellular network user distribution model
Appendix of heterogeneous cellular network user distribution modelAppendix of heterogeneous cellular network user distribution model
Appendix of heterogeneous cellular network user distribution model
 
2017 a
2017 a2017 a
2017 a
 
The reversible residual network
The reversible residual networkThe reversible residual network
The reversible residual network
 
Gate-Cs 2010
Gate-Cs 2010Gate-Cs 2010
Gate-Cs 2010
 
Backpropagation for Deep Learning
Backpropagation for Deep LearningBackpropagation for Deep Learning
Backpropagation for Deep Learning
 
Gate ee 2012 with solutions
Gate ee 2012 with solutionsGate ee 2012 with solutions
Gate ee 2012 with solutions
 
Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...
Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...
Quasistatic Fracture using Nonliner-Nonlocal Elastostatics with an Analytic T...
 
Gate ee 2003 with solutions
Gate ee 2003 with solutionsGate ee 2003 with solutions
Gate ee 2003 with solutions
 
20130912_mit _geordie_rose
20130912_mit _geordie_rose20130912_mit _geordie_rose
20130912_mit _geordie_rose
 
Backpropagation for Neural Networks
Backpropagation for Neural NetworksBackpropagation for Neural Networks
Backpropagation for Neural Networks
 
Forward secure asynchronous messaging from puncturable encryption
Forward secure asynchronous messaging from puncturable encryptionForward secure asynchronous messaging from puncturable encryption
Forward secure asynchronous messaging from puncturable encryption
 
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
論文紹介:Towards Robust Adaptive Object Detection Under Noisy Annotations
 
Digit recognizer by convolutional neural network
Digit recognizer by convolutional neural networkDigit recognizer by convolutional neural network
Digit recognizer by convolutional neural network
 
Gate-Cs 2006
Gate-Cs 2006Gate-Cs 2006
Gate-Cs 2006
 
Magical float repr
Magical float reprMagical float repr
Magical float repr
 
Quantum logic synthesis (srikanth)
Quantum logic synthesis (srikanth)Quantum logic synthesis (srikanth)
Quantum logic synthesis (srikanth)
 
Ma6251 MATHEMATICS III
Ma6251 MATHEMATICS IIIMa6251 MATHEMATICS III
Ma6251 MATHEMATICS III
 
Continuum Modeling and Control of Large Nonuniform Networks
Continuum Modeling and Control of Large Nonuniform NetworksContinuum Modeling and Control of Large Nonuniform Networks
Continuum Modeling and Control of Large Nonuniform Networks
 

Último

Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...only4webmaster01
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...amitlee9823
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysismanisha194592
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...amitlee9823
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionfulawalesam
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...amitlee9823
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...amitlee9823
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...SUHANI PANDEY
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxolyaivanovalion
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFxolyaivanovalion
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Researchmichael115558
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusTimothy Spann
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightDelhi Call girls
 

Último (20)

Anomaly detection and data imputation within time series
Anomaly detection and data imputation within time seriesAnomaly detection and data imputation within time series
Anomaly detection and data imputation within time series
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night StandCall Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Attibele ☎ 7737669865 🥵 Book Your One night Stand
 
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
Call Girls Indiranagar Just Call 👗 9155563397 👗 Top Class Call Girl Service B...
 
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men  🔝malwa🔝   Escorts Ser...
➥🔝 7737669865 🔝▻ malwa Call-girls in Women Seeking Men 🔝malwa🔝 Escorts Ser...
 
April 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's AnalysisApril 2024 - Crypto Market Report's Analysis
April 2024 - Crypto Market Report's Analysis
 
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
Call Girls Hsr Layout Just Call 👗 7737669865 👗 Top Class Call Girl Service Ba...
 
Week-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interactionWeek-01-2.ppt BBB human Computer interaction
Week-01-2.ppt BBB human Computer interaction
 
Predicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science ProjectPredicting Loan Approval: A Data Science Project
Predicting Loan Approval: A Data Science Project
 
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night StandCall Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Doddaballapur Road ☎ 7737669865 🥵 Book Your One night Stand
 
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
Vip Mumbai Call Girls Thane West Call On 9920725232 With Body to body massage...
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Surabaya ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night StandCall Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Hsr Layout ☎ 7737669865 🥵 Book Your One night Stand
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Midocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFxMidocean dropshipping via API with DroFx
Midocean dropshipping via API with DroFx
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Discover Why Less is More in B2B Research
Discover Why Less is More in B2B ResearchDiscover Why Less is More in B2B Research
Discover Why Less is More in B2B Research
 
Generative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and MilvusGenerative AI on Enterprise Cloud with NiFi and Milvus
Generative AI on Enterprise Cloud with NiFi and Milvus
 
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 nightCheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
Cheap Rate Call girls Sarita Vihar Delhi 9205541914 shot 1500 night
 

Cnn backpropagation derivation

  • 1. Backpropagation Derivation in Convolutional Neural Networks Punnoose A K punnoose07@gmail.com August 10, 2020 Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 1 / 30
  • 2. Contents 1 A simple CNN 2 Differential for various functions 3 Update equations for various CNN parameters 4 General order of update Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 2 / 30
  • 3. A simple 2 Layered, Depth 1 CNN X K J1 f C1 S1 G J2 f C2 S2 A Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 3 / 30
  • 4. Notations 1 X : Input feature. Assuming only 1 feature stream 2 K : Kernel. Depth 1 3 f : Rectified Linear Unit 4 C1 : First Convolution Output before ReLU 5 J1 : First Convolution Output after ReLU 6 S1 : Max Pooled Output, first layer 7 G : Kernel at second layer 8 C2 :Second Convolution Output before ReLU 9 J2 : Second Convolution Output after ReLU 10 S2 : Max Pooled Output, second layer 11 A : Flattened S2. I is the input size. A1 to AI 12 uij : weight between input and hidden layer 13 vjk: weight between hidden and output layer 14 yj : net input to hidden layer node j 15 zj : net input to output layer node j 16 bj : output of hidden layer node j 17 cj : output of output layer node j Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 4 / 30
  • 5. What is to be learned here? 1 uij for 1 ≤ i ≤ I, 1 ≤ j ≤ H 2 vjk for 1 ≤ j ≤ H, 1 ≤ k ≤ O 3 Kernel G 4 Kernel K Ignore the bias for time being Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 5 / 30
  • 6. CNN Operations 1 C1=relu(Convolution(X,K)) 2 S1=MaxPooling(C1) 3 C2=relu(Convolution(S1,G)) 4 S2=MaxPooling(C2) 5 A=flatten(S2) 6 Feed A as the input to the fully connected network 7 sigmoid function at hidden layer 8 softmax function at output layer 9 Cross entropy as the loss function Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 6 / 30
  • 7. Differential of Sigmoid Function Let f (x) = 1 1 + e−x f (x) = e−x (1 + e−x )2 = 1 1 + e−x e−x 1 + e−x = 1 1 + e−x (1 − 1 1 + e−x ) =f (x)(1 − f (x)) Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 7 / 30
  • 8. Differential of Softmax Function Softmax function is defined as fi = f (i; c1, c2...cO) = eci i eci For finding the differential, there are 2 cases. i.e, dfi dck where i = k and dfi dck , where i = k. Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 8 / 30
  • 9. Differential of Softmax Function For sake of simplicity consider 2 class output, i.e, O = 2. f1 = f (1; c1, c2) = ec1 ec1 + ec2 Case: i = k df1 dc1 = (ec1 + ec2 )ec1 − ec1 ec1 (ec1 + ec2 )2 = (ec1 + ec2 )ec1 (ec1 + ec2 )2 − ec1 ec1 (ec1 + ec2 )2 = ec1 (ec1 + ec2 ) − ec1 (ec1 + ec2 ) 2 = ec1 (ec1 + ec2 ) 1 − ec1 (ec1 + ec2 ) =f1(1 − f1) Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 9 / 30
  • 10. Differential of Softmax Function Case: i = k df1 dc2 = − ec1 ec2 (ec1 + es2 )2 = − ec1 (ec1 + es2 ) ec2 (ec1 + es2 ) = − f1f2 Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 10 / 30
  • 11. Differential of Softmax Function Generalizing, dfi dck = fi (1 − fi ) i = k −fi fk i = k Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 11 / 30
  • 12. Differential of Cross Entropy Loss Cross entropy loss between the output vector y and the target vector t of size O is given by L(y, t) = − O i yi log(ti ) dL dyi = − yi ti Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 12 / 30
  • 13. Differential of Rectified Linear Unit (ReLU) ReLU is defined as f (x) =max(0, x) df dx = 1 x > 0 0 otherwise In practise leaky ReLU is used, which is defined as f (x) =max(c0, x) df dx = 1 x > 0 c otherwise Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 13 / 30
  • 14. Differential of Max Pooling f (10, 20, 30, 40) = 40 Now if we increase 10 to 10.1, still f (10.1, 20, 30, 40) = 40 If we increase 30 to 30.1, still f (10.1, 20, 30, 40) = 40 Now if we increase 40 to 40.1, f (10.1, 20, 30, 40) = 40.1 if we increase 40 to 50, f (10.1, 20, 30, 50) = 50 The definition of differential is f (x) = limh→0 f (x+h)−f (x) h For the above function, the output changes linearly with the input(max). So f (a, b, c, d) = 1 Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 14 / 30
  • 15. Backpropagation at Hidden to Output Layer Input: X Output: c Target : t z c The output layer is divided into 2 sublayers shown in green and red. z is the weighted sum and is passed to all the output nodes. The layer in red actually performs the softmax operation and the softmax output is c. Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 15 / 30
  • 16. Derivation dL dvjk = dL dzk dzk dvjk dL dzk = O o=1 dL dco dco dzk = dL dck dck dzk + o=k dL dco dco dzk = − tk ck ck(1 − ck) + o=k −to co (−cock) = − tk(1 − ck) + o=k tock = − tk + tkck + o=k tock Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 16 / 30
  • 17. Derivation Continued = −tk + o=k tock + tkck = −tk + o tock = −tk + ck o to = −tk + ck1 dL dzk = ck − tk dzk dvjk =bj dL dvjk =(ck − tk)bj Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 17 / 30
  • 18. Backpropagation at Input to Hidden Layer dL duij = k=O k dL dzk dzk dbj dbj dyj dyj duij = dbj dyj dyj duij k dL dzk dzk dbj = bj (1 − bj )xi k (ck − tk)vjk Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 18 / 30
  • 19. Backpropagation for the kernels X K J1 f C1 S1 G J2 f C2 S2 A Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 19 / 30
  • 20. Backpropagation for kernel G We need to find dL dG and dL dK dL dG = dL dA dA dS2 dS2 dC2 dC2 dJ2 dJ2 dG As A = S2 flattened, dL dG = dL dS2 dS2 dC2 dC2 dJ2 dJ2 dG S2 is a max pooled version of C2. Operation wise, it is effectively selecting the max value out of a set of numbers. Change in non max value in the input set does not affect the output. A small change in max value value in the input set affect linearly in the output. So it can be said that maximum value out of a set, is locally linear. So dS2 dC2 = 1. Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 20 / 30
  • 21. Backpropagation for kernel G dL dG = dL dS2 dC2 dJ2 dJ2 dG = dL dJ2 dJ2 dG dL dS2 is dL dA written in square form. dL dAi = j k dL dzk dzk dbj dbj dyj dyj dAi = j k (ck − tk)vjkbj (1 − bj )uij dL dA =      dL dA1 dL dA2 ... dL dAI      Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 21 / 30
  • 22. Backpropagation for kernel G dL dS2 is dL dA written in square form. dL dS2 =   dL dA1 . . . . . . . dL dAI   dC2 dJ2 = 1 x > 0 c otherwise dL dG = dL dJ2 dJ2 dG =conv( dL dJ2 , S1) Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 22 / 30
  • 23. Backpropagation for the kernels X K J1 f C1 S1 G J2 f C2 S2 A Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 23 / 30
  • 24. Backpropagation for kernel K dL dK = conv(X, dL dJ1 ) We need to find dL dJ1 . dL dJ1 = dL dS1 dS1 dC1 dC1 dJ1 dC1 dJ1 = 1 x > 0 c otherwise dS1 dC1 =1 Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 24 / 30
  • 25. Backpropagation for kernel K dL dS1 = dJ2 dG Define G =1800 rotated G Then, dL dS1 =fullconv(G , dL dJ2 ) Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 25 / 30
  • 26. Full convolution explained G11G12 G21G22 1800 rotate to G22G21 G12G11 The convolution output is given as J2 = J211 J212 J221 J222 The input matrix can be written as S1= S131 S132 S133 S121 S122 S123 S111 S112 S113 Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 26 / 30
  • 27. Full convolution continued where, S111 =G11 dL dJ211 S112 =G12 dL dJ211 + G11 dL dJ212 S113 =G12 dL dJ212 S121 =G21 dL dJ211 + G11 dL dJ221 S122 =G22 dL dJ211 + G21 dL dJ212 + G12 dL dJ221 + G11 dL dJ222 S123 =G22 dL dJ212 + G12 dL dJ222 Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 27 / 30
  • 28. Full convolution continued S131 =G21 dL dJ221 S132 =G22 dL dJ221 + G21 dL dJ222 S133 =G22 dL dJ222 Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 28 / 30
  • 29. Order of update 1 Update hidden to output weights 2 Update input to hidden weights 3 Update kernel G 4 Update kernel K Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 29 / 30
  • 30. Queries?? Connect me at punnoose07@gmail.com Punnoose A K (punnoose07@gmail.com) Backpropagation Derivation in Convolutional Neural NetworksAugust 10, 2020 30 / 30