SlideShare a Scribd company logo
Back Propagation of Error in Neural Network
Subject: Machine Learning
Dr. Varun Kumar
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 1 / 12
Outlines
1 Introduction to Back Propagation Algorithm
2 Steps for Solving Back Propagation Problem
3 References
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 2 / 12
Introduction to Back Propagation Algorithm
Key Features of Back Propagation Algorithm:
1 Back-propagation is the essence of neural net training.
2 It is the practice of fine-tuning the weights of a neural net based on
the error rate (i.e. loss) obtained in the previous epoch (i.e. iteration).
3 Proper tuning of the weights ensures lower error rates, making the
model reliable by increasing its generalization.
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 3 / 12
Example
A simple neural network that have two input (x1, x2) and two output
(O1, O2). There is a single hidden layer in between input-output.
Q What will be the updated weight, so that total error value below the
0.001? ⇒ w∗
1 , w∗
2 , .....w∗
8 =??
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 4 / 12
Solution
⇒ As per the given question.
Input x1 = 0.05 and x2 = 0.10
Bias b1 = 0.35 and b2 = 0.60
Desired/target output O1 = 0.01 and O2 = 0.99
Learning rate η = 0.6
Initial weight w1 = 0.15, w2 = 0.25, w3 = 0.20, w4 = 0.30, w5 = 0.40,
w6 = 0.50, w7 = 0.45, w8 = 0.55
Condition, ETotal ≤ 0.001
Unknown w∗
1 , w∗
2 , .....w∗
8
⇒ From above figure, Input → Hidden layer
h1(in) = w1x1 + w2x2 + b1 (1)
h2(in) = w3x1 + w4x2 + b1 (2)
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 5 / 12
Continued–
Hidden Layer → O(in)
O1(in) = w5h1(out) + w6h2(out) + b2 (3)
O2(in) = w7h1(out) + w8h2(out) + b2 (4)
Relation between h1(in) and h1(out) or h2(in) and h2(out)
Here, we use the sigmoid function as an activation function
h1(out) =
1
1 + e−h1(in)
or h2(out) =
1
1 + e−h2(in)
(5)
Similarly, we can use the same activation function for finding the relation
between O1(in) and O1(out)
Note: As per the given question
O1(d) = 0.01 → Desired output across 1st node
O2(d) = 0.99 → Desired output across 2nd node
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 6 / 12
Continued–
From (1)
⇒ h1(in) = w1x1 + w2x2 + b1 = 0.15 × 0.05 + 0.25 × 0.10 + 0.35 = 0.385
⇒ h2(in) = w3x1 + w4x2 + b1 = 0.20 × 0.05 + 0.30 × 0.10 + 0.35 = 0.390
⇒ h1(out) = 1
1+e−h1(in) = 0.59508
⇒ h2(out) = 1
1+e−h2(in) = 0.59628
⇒ O1(in) = w5h1(in) + w6h2(in) + b2 = 0.40 × 0.385 + 0.50 × 0.390+
0.60 = 0.949
⇒ O2(in) = w7h1(in) + w8h2(in) + b2 = 0.45 × 0.385 + 0.55 × 0.390+
0.60 = 0.98775
⇒ O1(out) = 1
1+e−O1(in) = 0.72091 = Ô1 → Observed 1st output
⇒ O2(out) = 1
1+e−O2(in) = 0.72864 = Ô2 → Observed 2nd output
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 7 / 12
Continued–
⇒ Error observed across 1st output node.
EO1 =
1
2
(Ô1 − O1(d))2
=
1
2
(0.72091 − 0.01)2
= 0.2527
⇒ Error observed across 2nd output node.
EO2 =
1
2
(Ô2 − O2(d))2
=
1
2
(0.72864 − 0.01)2
= 0.2582
⇒ Total error Etot = EO1 + EO2 = 0.5109
Weight updation
Weight updation for hidden layer to O(in) node
⇒ Weight updation for W5
∂Etot
∂w5
=
∂Etot
∂O1(out)
×
∂O1(out)
∂O1(in)
×
∂O1(in)
∂w5
(6)
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 8 / 12
Continued–
⇒ ∂Etot
∂O1(out) = (Ô1 − O1(d)) = 0.72091 − 0.01 = 0.71091
⇒ ∂Etot
∂O1(in) = Ô1(1 − Ô1) = 0.72091(1 − 0.72091) = 0.2012
⇒ ∂O1(in)
∂w5
= h1(out) = 0.59508
⇒ New updated weight for w5
w∗
5 = w5(old) − η
∂Etot
∂w5
= 0.40 − 0.6 × 0.085117 = 0.34892
⇒ Note: In similar fashion, w∗
6 , w∗
7 , w∗
8 can also be calculated for a
single iteration. i.e,
⇒ w∗
6 = w6(old) − η∂Etot
∂w6
⇒ w∗
7 = w7(old) − η∂Etot
∂w7
⇒ w∗
8 = w8(old) − η∂Etot
∂w8
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 9 / 12
Continued–
Weight updation for input to hidden layer link, i.e. w∗
1 , w∗
2 , w∗
3 , w∗
4
Weight updation rule for w1
∂Etot
∂w1
=
∂Etot
∂h1(out)
×
∂h1(out)
∂h1(in)
×
∂h1(in)
∂w1
(7)
⇒
∂Etot
∂h1(out)
=
∂EO1
∂h1(out)
+
∂EO2
∂h1(out)
⇒
∂EO1
∂h1(out)
=
∂EO1
∂O1(out)
×
∂O1(out)
∂O1(in)
×
∂O1(in)
∂h1(out)
= (Ô1 − O1(d)) × Ô1(1 − Ô1) × w5
⇒
∂EO2
∂h1(out)
=
∂EO2
∂O2(out)
×
∂O2(out)
∂O2(in)
×
∂O2(in)
∂w1
= (Ô2 − O2(d)) × Ô2(1 − Ô2) × w7
⇒
∂Etot
∂h1(out)
= (Ô1 − O1(d)) × Ô1(1 − Ô1) × w5 + (Ô2 − O2(d)) × Ô2(1 − Ô2) × w7
⇒
∂h1(out)
∂h1(in)
= h1(in)(1 − h1(in)) = 0.385(1 − 0.385)
⇒
∂h1(in)
∂w1
= x1 = 0.05
w∗
1 = w1(old) − η
∂Etot
∂w1
(8)
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 10 / 12
Continued–
⇒ Note: In similar fashion, w∗
2 , w∗
3 , w∗
4 can also be calculated for a
single iteration. i.e,
⇒ w∗
2 = w2(old) − η∂Etot
∂w2
⇒ w∗
3 = w3(old) − η∂Etot
∂w3
⇒ w∗
4 = w4(old) − η∂Etot
∂w4
Note: This iteration process will be continued till the total error didn’t
approach to the certain threshold.
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 11 / 12
References
E. Alpaydin, Introduction to machine learning. MIT press, 2020.
J. Grus, Data science from scratch: first principles with python. O’Reilly Media,
2019.
T. M. Mitchell, The discipline of machine learning. Carnegie Mellon University,
School of Computer Science, Machine Learning , 2006, vol. 9.
Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 12 / 12

More Related Content

What's hot

Resolution method in AI.pptx
Resolution method in AI.pptxResolution method in AI.pptx
Resolution method in AI.pptx
Abdullah251975
 
Memory organization
Memory organizationMemory organization
Memory organization
ishapadhy
 
Addressing mode Computer Architecture
Addressing mode  Computer ArchitectureAddressing mode  Computer Architecture
Addressing mode Computer Architecture
Haris456
 
Input output organization
Input output organizationInput output organization
Input output organization
abdulugc
 
Parallel processing
Parallel processingParallel processing
Parallel processing
rajshreemuthiah
 
multiprocessors and multicomputers
 multiprocessors and multicomputers multiprocessors and multicomputers
multiprocessors and multicomputers
Pankaj Kumar Jain
 
Parallel processing
Parallel processingParallel processing
Parallel processing
Syed Zaid Irshad
 
Centralized shared memory architectures
Centralized shared memory architecturesCentralized shared memory architectures
Centralized shared memory architectures
Gokuldhev mony
 
Coa module1
Coa module1Coa module1
Coa module1
cs19club
 
Pipelining and ILP (Instruction Level Parallelism)
Pipelining and ILP (Instruction Level Parallelism) Pipelining and ILP (Instruction Level Parallelism)
Pipelining and ILP (Instruction Level Parallelism)
A B Shinde
 
04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks
Tamer Ahmed Farrag, PhD
 
Trace Scheduling
Trace SchedulingTrace Scheduling
Trace Scheduling
Min-Yih Hsu
 
Instruction set and instruction execution cycle
Instruction set and instruction execution cycleInstruction set and instruction execution cycle
Instruction set and instruction execution cycle
Mkaur01
 
Iv unit-fuzzification and de-fuzzification
Iv unit-fuzzification and de-fuzzificationIv unit-fuzzification and de-fuzzification
Iv unit-fuzzification and de-fuzzification
kypameenendranathred
 
Adaline madaline
Adaline madalineAdaline madaline
Adaline madaline
Nagarajan
 
Regularization in deep learning
Regularization in deep learningRegularization in deep learning
Regularization in deep learning
Kien Le
 
backpropagation in neural networks
backpropagation in neural networksbackpropagation in neural networks
backpropagation in neural networks
Akash Goel
 
Data Mining: Data cube computation and data generalization
Data Mining: Data cube computation and data generalizationData Mining: Data cube computation and data generalization
Data Mining: Data cube computation and data generalization
DataminingTools Inc
 
Interconnection Network
Interconnection NetworkInterconnection Network
Interconnection Network
Ali A Jalil
 
DMA Versus Polling or Interrupt Driven I/O
DMA Versus Polling or Interrupt Driven I/ODMA Versus Polling or Interrupt Driven I/O
DMA Versus Polling or Interrupt Driven I/O
sathish sak
 

What's hot (20)

Resolution method in AI.pptx
Resolution method in AI.pptxResolution method in AI.pptx
Resolution method in AI.pptx
 
Memory organization
Memory organizationMemory organization
Memory organization
 
Addressing mode Computer Architecture
Addressing mode  Computer ArchitectureAddressing mode  Computer Architecture
Addressing mode Computer Architecture
 
Input output organization
Input output organizationInput output organization
Input output organization
 
Parallel processing
Parallel processingParallel processing
Parallel processing
 
multiprocessors and multicomputers
 multiprocessors and multicomputers multiprocessors and multicomputers
multiprocessors and multicomputers
 
Parallel processing
Parallel processingParallel processing
Parallel processing
 
Centralized shared memory architectures
Centralized shared memory architecturesCentralized shared memory architectures
Centralized shared memory architectures
 
Coa module1
Coa module1Coa module1
Coa module1
 
Pipelining and ILP (Instruction Level Parallelism)
Pipelining and ILP (Instruction Level Parallelism) Pipelining and ILP (Instruction Level Parallelism)
Pipelining and ILP (Instruction Level Parallelism)
 
04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward Networks
 
Trace Scheduling
Trace SchedulingTrace Scheduling
Trace Scheduling
 
Instruction set and instruction execution cycle
Instruction set and instruction execution cycleInstruction set and instruction execution cycle
Instruction set and instruction execution cycle
 
Iv unit-fuzzification and de-fuzzification
Iv unit-fuzzification and de-fuzzificationIv unit-fuzzification and de-fuzzification
Iv unit-fuzzification and de-fuzzification
 
Adaline madaline
Adaline madalineAdaline madaline
Adaline madaline
 
Regularization in deep learning
Regularization in deep learningRegularization in deep learning
Regularization in deep learning
 
backpropagation in neural networks
backpropagation in neural networksbackpropagation in neural networks
backpropagation in neural networks
 
Data Mining: Data cube computation and data generalization
Data Mining: Data cube computation and data generalizationData Mining: Data cube computation and data generalization
Data Mining: Data cube computation and data generalization
 
Interconnection Network
Interconnection NetworkInterconnection Network
Interconnection Network
 
DMA Versus Polling or Interrupt Driven I/O
DMA Versus Polling or Interrupt Driven I/ODMA Versus Polling or Interrupt Driven I/O
DMA Versus Polling or Interrupt Driven I/O
 

Similar to Back Propagation in Deep Neural Network

Backpropagation Algorithm forward and backward pass
Backpropagation Algorithm forward and backward passBackpropagation Algorithm forward and backward pass
Backpropagation Algorithm forward and backward pass
ssuser7e0a0e
 
backprop.ppt
backprop.pptbackprop.ppt
backprop.ppt
neelamsanjeevkumar
 
Perfect method for Frames
Perfect method for FramesPerfect method for Frames
Perfect method for Frames
andreslahe
 
Lecture 9 (Digital Image Processing)
Lecture 9 (Digital Image Processing)Lecture 9 (Digital Image Processing)
Lecture 9 (Digital Image Processing)
VARUN KUMAR
 
Newton two Equation method
Newton two Equation  method Newton two Equation  method
Newton two Equation method
shanto017
 
Data mining assignment 5
Data mining assignment 5Data mining assignment 5
Data mining assignment 5
BarryK88
 
Multilayer perceptron
Multilayer perceptronMultilayer perceptron
Multilayer perceptron
smitamm
 
5 Introduction to neural networks
5 Introduction to neural networks5 Introduction to neural networks
5 Introduction to neural networks
Dmytro Fishman
 
Lecture 2: Artificial Neural Network
Lecture 2: Artificial Neural NetworkLecture 2: Artificial Neural Network
Lecture 2: Artificial Neural Network
Mohamed Loey
 
Fast and efficient exact synthesis of single qubit unitaries generated by cli...
Fast and efficient exact synthesis of single qubit unitaries generated by cli...Fast and efficient exact synthesis of single qubit unitaries generated by cli...
Fast and efficient exact synthesis of single qubit unitaries generated by cli...
JamesMa54
 
Neural Network - Feed Forward - Back Propagation Visualization
Neural Network - Feed Forward - Back Propagation VisualizationNeural Network - Feed Forward - Back Propagation Visualization
Neural Network - Feed Forward - Back Propagation Visualization
Traian Morar
 
Minor 1 11th paper.pdf
Minor 1 11th paper.pdfMinor 1 11th paper.pdf
Minor 1 11th paper.pdf
ssuser33d0b9
 
Back prop
Back propBack prop
Back prop
Md Razaul Karim
 
Top school in India
Top school in IndiaTop school in India
Top school in India
Edhole.com
 
Artificial Neural Networks
Artificial Neural NetworksArtificial Neural Networks
Artificial Neural Networks
Stefano Dalla Palma
 
Top School in delhi
Top School in delhiTop School in delhi
Top School in delhi
Edhole.com
 
NN-Ch6.PDF
NN-Ch6.PDFNN-Ch6.PDF
NN-Ch6.PDF
gnans Kgnanshek
 
Introduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from ScratchIntroduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from Scratch
Ahmed BESBES
 
Laplace equation
Laplace equationLaplace equation
Laplace equation
alexkhan129
 
NN-Ch2.PDF
NN-Ch2.PDFNN-Ch2.PDF
NN-Ch2.PDF
gnans Kgnanshek
 

Similar to Back Propagation in Deep Neural Network (20)

Backpropagation Algorithm forward and backward pass
Backpropagation Algorithm forward and backward passBackpropagation Algorithm forward and backward pass
Backpropagation Algorithm forward and backward pass
 
backprop.ppt
backprop.pptbackprop.ppt
backprop.ppt
 
Perfect method for Frames
Perfect method for FramesPerfect method for Frames
Perfect method for Frames
 
Lecture 9 (Digital Image Processing)
Lecture 9 (Digital Image Processing)Lecture 9 (Digital Image Processing)
Lecture 9 (Digital Image Processing)
 
Newton two Equation method
Newton two Equation  method Newton two Equation  method
Newton two Equation method
 
Data mining assignment 5
Data mining assignment 5Data mining assignment 5
Data mining assignment 5
 
Multilayer perceptron
Multilayer perceptronMultilayer perceptron
Multilayer perceptron
 
5 Introduction to neural networks
5 Introduction to neural networks5 Introduction to neural networks
5 Introduction to neural networks
 
Lecture 2: Artificial Neural Network
Lecture 2: Artificial Neural NetworkLecture 2: Artificial Neural Network
Lecture 2: Artificial Neural Network
 
Fast and efficient exact synthesis of single qubit unitaries generated by cli...
Fast and efficient exact synthesis of single qubit unitaries generated by cli...Fast and efficient exact synthesis of single qubit unitaries generated by cli...
Fast and efficient exact synthesis of single qubit unitaries generated by cli...
 
Neural Network - Feed Forward - Back Propagation Visualization
Neural Network - Feed Forward - Back Propagation VisualizationNeural Network - Feed Forward - Back Propagation Visualization
Neural Network - Feed Forward - Back Propagation Visualization
 
Minor 1 11th paper.pdf
Minor 1 11th paper.pdfMinor 1 11th paper.pdf
Minor 1 11th paper.pdf
 
Back prop
Back propBack prop
Back prop
 
Top school in India
Top school in IndiaTop school in India
Top school in India
 
Artificial Neural Networks
Artificial Neural NetworksArtificial Neural Networks
Artificial Neural Networks
 
Top School in delhi
Top School in delhiTop School in delhi
Top School in delhi
 
NN-Ch6.PDF
NN-Ch6.PDFNN-Ch6.PDF
NN-Ch6.PDF
 
Introduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from ScratchIntroduction to Neural Networks and Deep Learning from Scratch
Introduction to Neural Networks and Deep Learning from Scratch
 
Laplace equation
Laplace equationLaplace equation
Laplace equation
 
NN-Ch2.PDF
NN-Ch2.PDFNN-Ch2.PDF
NN-Ch2.PDF
 

More from VARUN KUMAR

Distributed rc Model
Distributed rc ModelDistributed rc Model
Distributed rc Model
VARUN KUMAR
 
Electrical Wire Model
Electrical Wire ModelElectrical Wire Model
Electrical Wire Model
VARUN KUMAR
 
Interconnect Parameter in Digital VLSI Design
Interconnect Parameter in Digital VLSI DesignInterconnect Parameter in Digital VLSI Design
Interconnect Parameter in Digital VLSI Design
VARUN KUMAR
 
Introduction to Digital VLSI Design
Introduction to Digital VLSI DesignIntroduction to Digital VLSI Design
Introduction to Digital VLSI Design
VARUN KUMAR
 
Challenges of Massive MIMO System
Challenges of Massive MIMO SystemChallenges of Massive MIMO System
Challenges of Massive MIMO System
VARUN KUMAR
 
E-democracy or Digital Democracy
E-democracy or Digital DemocracyE-democracy or Digital Democracy
E-democracy or Digital Democracy
VARUN KUMAR
 
Ethics of Parasitic Computing
Ethics of Parasitic ComputingEthics of Parasitic Computing
Ethics of Parasitic Computing
VARUN KUMAR
 
Action Lines of Geneva Plan of Action
Action Lines of Geneva Plan of ActionAction Lines of Geneva Plan of Action
Action Lines of Geneva Plan of Action
VARUN KUMAR
 
Geneva Plan of Action
Geneva Plan of ActionGeneva Plan of Action
Geneva Plan of Action
VARUN KUMAR
 
Fair Use in the Electronic Age
Fair Use in the Electronic AgeFair Use in the Electronic Age
Fair Use in the Electronic Age
VARUN KUMAR
 
Software as a Property
Software as a PropertySoftware as a Property
Software as a Property
VARUN KUMAR
 
Orthogonal Polynomial
Orthogonal PolynomialOrthogonal Polynomial
Orthogonal Polynomial
VARUN KUMAR
 
Patent Protection
Patent ProtectionPatent Protection
Patent Protection
VARUN KUMAR
 
Copyright Vs Patent and Trade Secrecy Law
Copyright Vs Patent and Trade Secrecy LawCopyright Vs Patent and Trade Secrecy Law
Copyright Vs Patent and Trade Secrecy Law
VARUN KUMAR
 
Property Right and Software
Property Right and SoftwareProperty Right and Software
Property Right and Software
VARUN KUMAR
 
Investigating Data Trials
Investigating Data TrialsInvestigating Data Trials
Investigating Data Trials
VARUN KUMAR
 
Gaussian Numerical Integration
Gaussian Numerical IntegrationGaussian Numerical Integration
Gaussian Numerical Integration
VARUN KUMAR
 
Censorship and Controversy
Censorship and ControversyCensorship and Controversy
Censorship and Controversy
VARUN KUMAR
 
Romberg's Integration
Romberg's IntegrationRomberg's Integration
Romberg's Integration
VARUN KUMAR
 
Introduction to Censorship
Introduction to Censorship Introduction to Censorship
Introduction to Censorship
VARUN KUMAR
 

More from VARUN KUMAR (20)

Distributed rc Model
Distributed rc ModelDistributed rc Model
Distributed rc Model
 
Electrical Wire Model
Electrical Wire ModelElectrical Wire Model
Electrical Wire Model
 
Interconnect Parameter in Digital VLSI Design
Interconnect Parameter in Digital VLSI DesignInterconnect Parameter in Digital VLSI Design
Interconnect Parameter in Digital VLSI Design
 
Introduction to Digital VLSI Design
Introduction to Digital VLSI DesignIntroduction to Digital VLSI Design
Introduction to Digital VLSI Design
 
Challenges of Massive MIMO System
Challenges of Massive MIMO SystemChallenges of Massive MIMO System
Challenges of Massive MIMO System
 
E-democracy or Digital Democracy
E-democracy or Digital DemocracyE-democracy or Digital Democracy
E-democracy or Digital Democracy
 
Ethics of Parasitic Computing
Ethics of Parasitic ComputingEthics of Parasitic Computing
Ethics of Parasitic Computing
 
Action Lines of Geneva Plan of Action
Action Lines of Geneva Plan of ActionAction Lines of Geneva Plan of Action
Action Lines of Geneva Plan of Action
 
Geneva Plan of Action
Geneva Plan of ActionGeneva Plan of Action
Geneva Plan of Action
 
Fair Use in the Electronic Age
Fair Use in the Electronic AgeFair Use in the Electronic Age
Fair Use in the Electronic Age
 
Software as a Property
Software as a PropertySoftware as a Property
Software as a Property
 
Orthogonal Polynomial
Orthogonal PolynomialOrthogonal Polynomial
Orthogonal Polynomial
 
Patent Protection
Patent ProtectionPatent Protection
Patent Protection
 
Copyright Vs Patent and Trade Secrecy Law
Copyright Vs Patent and Trade Secrecy LawCopyright Vs Patent and Trade Secrecy Law
Copyright Vs Patent and Trade Secrecy Law
 
Property Right and Software
Property Right and SoftwareProperty Right and Software
Property Right and Software
 
Investigating Data Trials
Investigating Data TrialsInvestigating Data Trials
Investigating Data Trials
 
Gaussian Numerical Integration
Gaussian Numerical IntegrationGaussian Numerical Integration
Gaussian Numerical Integration
 
Censorship and Controversy
Censorship and ControversyCensorship and Controversy
Censorship and Controversy
 
Romberg's Integration
Romberg's IntegrationRomberg's Integration
Romberg's Integration
 
Introduction to Censorship
Introduction to Censorship Introduction to Censorship
Introduction to Censorship
 

Recently uploaded

一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
upoux
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
Divyanshu
 
Open Channel Flow: fluid flow with a free surface
Open Channel Flow: fluid flow with a free surfaceOpen Channel Flow: fluid flow with a free surface
Open Channel Flow: fluid flow with a free surface
Indrajeet sahu
 
Asymmetrical Repulsion Magnet Motor Ratio 6-7.pdf
Asymmetrical Repulsion Magnet Motor Ratio 6-7.pdfAsymmetrical Repulsion Magnet Motor Ratio 6-7.pdf
Asymmetrical Repulsion Magnet Motor Ratio 6-7.pdf
felixwold
 
Mechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdfMechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdf
21UME003TUSHARDEB
 
Ericsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.pptEricsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.ppt
wafawafa52
 
Transformers design and coooling methods
Transformers design and coooling methodsTransformers design and coooling methods
Transformers design and coooling methods
Roger Rozario
 
Accident detection system project report.pdf
Accident detection system project report.pdfAccident detection system project report.pdf
Accident detection system project report.pdf
Kamal Acharya
 
FULL STACK PROGRAMMING - Both Front End and Back End
FULL STACK PROGRAMMING - Both Front End and Back EndFULL STACK PROGRAMMING - Both Front End and Back End
FULL STACK PROGRAMMING - Both Front End and Back End
PreethaV16
 
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
upoux
 
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Transcat
 
ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
VANDANAMOHANGOUDA
 
Unit -II Spectroscopy - EC I B.Tech.pdf
Unit -II Spectroscopy - EC  I B.Tech.pdfUnit -II Spectroscopy - EC  I B.Tech.pdf
Unit -II Spectroscopy - EC I B.Tech.pdf
TeluguBadi
 
Zener Diode and its V-I Characteristics and Applications
Zener Diode and its V-I Characteristics and ApplicationsZener Diode and its V-I Characteristics and Applications
Zener Diode and its V-I Characteristics and Applications
Shiny Christobel
 
Blood finder application project report (1).pdf
Blood finder application project report (1).pdfBlood finder application project report (1).pdf
Blood finder application project report (1).pdf
Kamal Acharya
 
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
OKORIE1
 
SENTIMENT ANALYSIS ON PPT AND Project template_.pptx
SENTIMENT ANALYSIS ON PPT AND Project template_.pptxSENTIMENT ANALYSIS ON PPT AND Project template_.pptx
SENTIMENT ANALYSIS ON PPT AND Project template_.pptx
b0754201
 
Impartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 StandardImpartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 Standard
MuhammadJazib15
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
uqyfuc
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
ecqow
 

Recently uploaded (20)

一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
一比一原版(osu毕业证书)美国俄勒冈州立大学毕业证如何办理
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
 
Open Channel Flow: fluid flow with a free surface
Open Channel Flow: fluid flow with a free surfaceOpen Channel Flow: fluid flow with a free surface
Open Channel Flow: fluid flow with a free surface
 
Asymmetrical Repulsion Magnet Motor Ratio 6-7.pdf
Asymmetrical Repulsion Magnet Motor Ratio 6-7.pdfAsymmetrical Repulsion Magnet Motor Ratio 6-7.pdf
Asymmetrical Repulsion Magnet Motor Ratio 6-7.pdf
 
Mechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdfMechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdf
 
Ericsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.pptEricsson LTE Throughput Troubleshooting Techniques.ppt
Ericsson LTE Throughput Troubleshooting Techniques.ppt
 
Transformers design and coooling methods
Transformers design and coooling methodsTransformers design and coooling methods
Transformers design and coooling methods
 
Accident detection system project report.pdf
Accident detection system project report.pdfAccident detection system project report.pdf
Accident detection system project report.pdf
 
FULL STACK PROGRAMMING - Both Front End and Back End
FULL STACK PROGRAMMING - Both Front End and Back EndFULL STACK PROGRAMMING - Both Front End and Back End
FULL STACK PROGRAMMING - Both Front End and Back End
 
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
 
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
Tools & Techniques for Commissioning and Maintaining PV Systems W-Animations ...
 
ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
 
Unit -II Spectroscopy - EC I B.Tech.pdf
Unit -II Spectroscopy - EC  I B.Tech.pdfUnit -II Spectroscopy - EC  I B.Tech.pdf
Unit -II Spectroscopy - EC I B.Tech.pdf
 
Zener Diode and its V-I Characteristics and Applications
Zener Diode and its V-I Characteristics and ApplicationsZener Diode and its V-I Characteristics and Applications
Zener Diode and its V-I Characteristics and Applications
 
Blood finder application project report (1).pdf
Blood finder application project report (1).pdfBlood finder application project report (1).pdf
Blood finder application project report (1).pdf
 
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
DESIGN AND MANUFACTURE OF CEILING BOARD USING SAWDUST AND WASTE CARTON MATERI...
 
SENTIMENT ANALYSIS ON PPT AND Project template_.pptx
SENTIMENT ANALYSIS ON PPT AND Project template_.pptxSENTIMENT ANALYSIS ON PPT AND Project template_.pptx
SENTIMENT ANALYSIS ON PPT AND Project template_.pptx
 
Impartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 StandardImpartiality as per ISO /IEC 17025:2017 Standard
Impartiality as per ISO /IEC 17025:2017 Standard
 
一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理一比一原版(USF毕业证)旧金山大学毕业证如何办理
一比一原版(USF毕业证)旧金山大学毕业证如何办理
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
 

Back Propagation in Deep Neural Network

  • 1. Back Propagation of Error in Neural Network Subject: Machine Learning Dr. Varun Kumar Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 1 / 12
  • 2. Outlines 1 Introduction to Back Propagation Algorithm 2 Steps for Solving Back Propagation Problem 3 References Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 2 / 12
  • 3. Introduction to Back Propagation Algorithm Key Features of Back Propagation Algorithm: 1 Back-propagation is the essence of neural net training. 2 It is the practice of fine-tuning the weights of a neural net based on the error rate (i.e. loss) obtained in the previous epoch (i.e. iteration). 3 Proper tuning of the weights ensures lower error rates, making the model reliable by increasing its generalization. Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 3 / 12
  • 4. Example A simple neural network that have two input (x1, x2) and two output (O1, O2). There is a single hidden layer in between input-output. Q What will be the updated weight, so that total error value below the 0.001? ⇒ w∗ 1 , w∗ 2 , .....w∗ 8 =?? Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 4 / 12
  • 5. Solution ⇒ As per the given question. Input x1 = 0.05 and x2 = 0.10 Bias b1 = 0.35 and b2 = 0.60 Desired/target output O1 = 0.01 and O2 = 0.99 Learning rate η = 0.6 Initial weight w1 = 0.15, w2 = 0.25, w3 = 0.20, w4 = 0.30, w5 = 0.40, w6 = 0.50, w7 = 0.45, w8 = 0.55 Condition, ETotal ≤ 0.001 Unknown w∗ 1 , w∗ 2 , .....w∗ 8 ⇒ From above figure, Input → Hidden layer h1(in) = w1x1 + w2x2 + b1 (1) h2(in) = w3x1 + w4x2 + b1 (2) Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 5 / 12
  • 6. Continued– Hidden Layer → O(in) O1(in) = w5h1(out) + w6h2(out) + b2 (3) O2(in) = w7h1(out) + w8h2(out) + b2 (4) Relation between h1(in) and h1(out) or h2(in) and h2(out) Here, we use the sigmoid function as an activation function h1(out) = 1 1 + e−h1(in) or h2(out) = 1 1 + e−h2(in) (5) Similarly, we can use the same activation function for finding the relation between O1(in) and O1(out) Note: As per the given question O1(d) = 0.01 → Desired output across 1st node O2(d) = 0.99 → Desired output across 2nd node Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 6 / 12
  • 7. Continued– From (1) ⇒ h1(in) = w1x1 + w2x2 + b1 = 0.15 × 0.05 + 0.25 × 0.10 + 0.35 = 0.385 ⇒ h2(in) = w3x1 + w4x2 + b1 = 0.20 × 0.05 + 0.30 × 0.10 + 0.35 = 0.390 ⇒ h1(out) = 1 1+e−h1(in) = 0.59508 ⇒ h2(out) = 1 1+e−h2(in) = 0.59628 ⇒ O1(in) = w5h1(in) + w6h2(in) + b2 = 0.40 × 0.385 + 0.50 × 0.390+ 0.60 = 0.949 ⇒ O2(in) = w7h1(in) + w8h2(in) + b2 = 0.45 × 0.385 + 0.55 × 0.390+ 0.60 = 0.98775 ⇒ O1(out) = 1 1+e−O1(in) = 0.72091 = Ô1 → Observed 1st output ⇒ O2(out) = 1 1+e−O2(in) = 0.72864 = Ô2 → Observed 2nd output Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 7 / 12
  • 8. Continued– ⇒ Error observed across 1st output node. EO1 = 1 2 (Ô1 − O1(d))2 = 1 2 (0.72091 − 0.01)2 = 0.2527 ⇒ Error observed across 2nd output node. EO2 = 1 2 (Ô2 − O2(d))2 = 1 2 (0.72864 − 0.01)2 = 0.2582 ⇒ Total error Etot = EO1 + EO2 = 0.5109 Weight updation Weight updation for hidden layer to O(in) node ⇒ Weight updation for W5 ∂Etot ∂w5 = ∂Etot ∂O1(out) × ∂O1(out) ∂O1(in) × ∂O1(in) ∂w5 (6) Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 8 / 12
  • 9. Continued– ⇒ ∂Etot ∂O1(out) = (Ô1 − O1(d)) = 0.72091 − 0.01 = 0.71091 ⇒ ∂Etot ∂O1(in) = Ô1(1 − Ô1) = 0.72091(1 − 0.72091) = 0.2012 ⇒ ∂O1(in) ∂w5 = h1(out) = 0.59508 ⇒ New updated weight for w5 w∗ 5 = w5(old) − η ∂Etot ∂w5 = 0.40 − 0.6 × 0.085117 = 0.34892 ⇒ Note: In similar fashion, w∗ 6 , w∗ 7 , w∗ 8 can also be calculated for a single iteration. i.e, ⇒ w∗ 6 = w6(old) − η∂Etot ∂w6 ⇒ w∗ 7 = w7(old) − η∂Etot ∂w7 ⇒ w∗ 8 = w8(old) − η∂Etot ∂w8 Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 9 / 12
  • 10. Continued– Weight updation for input to hidden layer link, i.e. w∗ 1 , w∗ 2 , w∗ 3 , w∗ 4 Weight updation rule for w1 ∂Etot ∂w1 = ∂Etot ∂h1(out) × ∂h1(out) ∂h1(in) × ∂h1(in) ∂w1 (7) ⇒ ∂Etot ∂h1(out) = ∂EO1 ∂h1(out) + ∂EO2 ∂h1(out) ⇒ ∂EO1 ∂h1(out) = ∂EO1 ∂O1(out) × ∂O1(out) ∂O1(in) × ∂O1(in) ∂h1(out) = (Ô1 − O1(d)) × Ô1(1 − Ô1) × w5 ⇒ ∂EO2 ∂h1(out) = ∂EO2 ∂O2(out) × ∂O2(out) ∂O2(in) × ∂O2(in) ∂w1 = (Ô2 − O2(d)) × Ô2(1 − Ô2) × w7 ⇒ ∂Etot ∂h1(out) = (Ô1 − O1(d)) × Ô1(1 − Ô1) × w5 + (Ô2 − O2(d)) × Ô2(1 − Ô2) × w7 ⇒ ∂h1(out) ∂h1(in) = h1(in)(1 − h1(in)) = 0.385(1 − 0.385) ⇒ ∂h1(in) ∂w1 = x1 = 0.05 w∗ 1 = w1(old) − η ∂Etot ∂w1 (8) Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 10 / 12
  • 11. Continued– ⇒ Note: In similar fashion, w∗ 2 , w∗ 3 , w∗ 4 can also be calculated for a single iteration. i.e, ⇒ w∗ 2 = w2(old) − η∂Etot ∂w2 ⇒ w∗ 3 = w3(old) − η∂Etot ∂w3 ⇒ w∗ 4 = w4(old) − η∂Etot ∂w4 Note: This iteration process will be continued till the total error didn’t approach to the certain threshold. Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 11 / 12
  • 12. References E. Alpaydin, Introduction to machine learning. MIT press, 2020. J. Grus, Data science from scratch: first principles with python. O’Reilly Media, 2019. T. M. Mitchell, The discipline of machine learning. Carnegie Mellon University, School of Computer Science, Machine Learning , 2006, vol. 9. Subject: Machine Learning Dr. Varun Kumar (IIIT Surat) Machine Learning 12 / 12