SlideShare a Scribd company logo
1 of 25
Download to read offline
Deep Neural Network
RTSS JUN YOUNG PARK
Reference
◦ R을 활용한 기계 학습 – Brett Lantz 著
◦ 2017-1학기 ‘현대사회와 빅데이터‘ 교재
◦ 데이터 전처리/표본 분석 과정 참조
Number of Parameters
From the last presentation …
How many parameters in this linear model ?
X W b S(Y)Y
0
1
0
0
0
Dog !
x
Test data (Image)
[1024x768] image
5 Classes
𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆 𝑊𝑊 + 𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆 𝐵𝐵 = 𝐼𝐼 𝐼𝐼𝐼𝐼𝐼𝐼𝐼𝐼_𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠 ∗ 𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶 + 𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶 = 3,932,165
Go Deep & Wide !
W1 W2 W3 ?
[784, 256] [256, 256] [256, 10]
Hidden Layer
[10]32
32
X Y
Invisible from the input/output.
Rectified Linear Units
◦ Why not Sigmoid ?
◦ Input signal may too near to 0 during back propagation. (Vanishing Gradient)
𝑅𝑅 𝑥𝑥 = �
𝑥𝑥, 𝑥𝑥 ≥ 0
0, 𝑥𝑥 < 0
𝜕𝜕
𝜕𝜕𝜕𝜕
{𝑅𝑅 𝑥𝑥 } = �
1, 𝑥𝑥 ≥ 0
0, 𝑥𝑥 < 0
Also …
Weight Initialization
◦ DBN (Deep Belief Networks )
◦ Process RBM for training each 2 layers
◦ After initialization -> We just need fine tuning(Training).
◦ Using Gaussian random number
◦ Xavier (2010)
◦ Divide Gaussian random number into number of inputs.
◦ He (2015)
◦ Divide the result of Xavier number into 2.
L2 Regularization
◦ Large weight may bend the model.
◦ To avoid ‘Large Weight’, We use the term below
ℒ =
1
𝑁𝑁
�
𝑖𝑖
𝐷𝐷 𝑆𝑆 𝑊𝑊𝑥𝑥𝑖𝑖 + 𝑏𝑏 , 𝐿𝐿𝑖𝑖 + 𝜆𝜆 � 𝑊𝑊2
0 ≤ 𝜆𝜆 ≤ 1 : Regularization strength
Dropout
◦ Forces the network to have redundant representation
While Testing : No Dropout While Training : Apply Dropout
Chain Rule
F GX Y
y = 𝑔𝑔(𝑓𝑓 𝑥𝑥 )
FX G’ *
y′
= 𝑔𝑔′
𝑓𝑓 𝑥𝑥 ∗ 𝑓𝑓𝑓(𝑥𝑥)
F’
X
Y’
◦ To make back propagation easier, We use operation graph like below.
Back Propagation
◦ Get derivatives using ‘Back Propagation’
+
𝑥𝑥
𝑦𝑦
𝑧𝑧
𝑧𝑧 = 𝑥𝑥 + 𝑦𝑦
𝜕𝜕𝑧𝑧
𝜕𝜕𝜕𝜕
=
𝜕𝜕𝜕𝜕
𝜕𝜕𝑦𝑦
= 1
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
𝜕𝜕𝑧𝑧
𝜕𝜕𝜕𝜕
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
𝜕𝜕𝑧𝑧
𝜕𝜕𝑦𝑦
x
𝑥𝑥
𝑦𝑦
𝑧𝑧
𝑧𝑧 = 𝑥𝑥𝑥𝑥
𝜕𝜕𝑧𝑧
𝜕𝜕𝜕𝜕
= 𝑦𝑦,
𝜕𝜕𝜕𝜕
𝜕𝜕𝑦𝑦
= 𝑥𝑥
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
𝜕𝜕𝑧𝑧
𝜕𝜕𝜕𝜕
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
𝜕𝜕𝑧𝑧
𝜕𝜕𝑦𝑦
𝑦𝑦 �
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
𝑥𝑥 �
𝜕𝜕𝐿𝐿
𝜕𝜕𝑧𝑧
For signal 𝐿𝐿 …
Ensemble Learning
Practical Use
◦ Breast cancer diagnosis using ‘Deep Neural Network’
◦ The example from the book ‘Machine Learning with R’
◦ Using the dataset from ‘University of Wisconsin’
◦ The dataset includes 32 features
◦ Diagnosis, Radius, Perimeter, Area … and so on
Import/Define Methods
◦ Import packages for NumPy and TF
◦ Define the method for normalization
𝑧𝑧𝑛𝑛 =
𝑥𝑥𝑛𝑛 − min(𝒙𝒙)
max 𝒙𝒙 − min(𝒙𝒙)
Import Dataset
◦ Dataset from University of Wisconsin.
◦ Exclude unused feature (ID).
◦ Divide dataset for x and y.
One-Hot Encoding
‘M’
[1, 0]
[0, 1]
Malignant
Benign
Divide Dataset
No Cheating !
Design Neural Network
Build Session
◦ Can control forced/unforced.
◦ Restore previous trained weights.
◦ Write log for TensorBoard.
Training Neurons
◦ 10001 steps per a run.
◦ Add summary for Tensorboard.
Save Results and Get Accuracy
◦ Save previous training data to keep current weight and bias
◦ Each run trains 10001 times
Result #1
<1st Attempt> <2nd Attempt>
Attempt more …
To use Xavier initializer
Result #2
96.27% -> 97.01% 97.01% -> 97.76%
Self Test
◦ 모델의 Parameter 수는 어떻게 결정되는지 설명하라.
◦ ReLU 함수의 개형과 그 미분의 결과는 어떻게 되는지 Sigmoid 함수와 비교하여 설명하라.
◦ Weight Initialization 의 목적과 그 방법을 설명하라.
◦ L2 Regularization 의 목적과 그 원리를 설명하라.
◦ Dropout 은 왜 필요한가 ? 또 훈련/시험시에 어떻게 설정해야 적절한가 ?
◦ NN 에 있어 Back Propagation 이 왜 유리한가?
◦ Ensemble Learning 에 대하여 설명하라.

More Related Content

What's hot

Object classification using deep neural network
Object classification using deep neural networkObject classification using deep neural network
Object classification using deep neural networknishakushwah4
 
2013.10.24 big datavisualization
2013.10.24 big datavisualization2013.10.24 big datavisualization
2013.10.24 big datavisualizationSean Kandel
 
Detecting early-stage neurodegeneration using 3D ConvNet
Detecting early-stage neurodegeneration using 3D ConvNet Detecting early-stage neurodegeneration using 3D ConvNet
Detecting early-stage neurodegeneration using 3D ConvNet Chun-Ming Chang
 
Structured Forests for Fast Edge Detection [Paper Presentation]
Structured Forests for Fast Edge Detection [Paper Presentation]Structured Forests for Fast Edge Detection [Paper Presentation]
Structured Forests for Fast Edge Detection [Paper Presentation]Mohammad Shaker
 
3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...
3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...
3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...EL-Hachemi Guerrout
 
Lecture 6 Basic Transform: Translation, Rotation, Scaling
Lecture 6 Basic Transform: Translation, Rotation, ScalingLecture 6 Basic Transform: Translation, Rotation, Scaling
Lecture 6 Basic Transform: Translation, Rotation, ScalingVARUN KUMAR
 
Erik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better MortgageErik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better MortgageMLconf
 
Using parallel programming to improve performance of image processing
Using parallel programming to improve performance of image processingUsing parallel programming to improve performance of image processing
Using parallel programming to improve performance of image processingChan Le
 
Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...
Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...
Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...MLconf
 
Introduction to ml and dl
Introduction to ml and dlIntroduction to ml and dl
Introduction to ml and dlSuyashSingh70
 
Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems Scandala Tamang
 
Lecture32
Lecture32Lecture32
Lecture32zukun
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 

What's hot (20)

Object classification using deep neural network
Object classification using deep neural networkObject classification using deep neural network
Object classification using deep neural network
 
2013.10.24 big datavisualization
2013.10.24 big datavisualization2013.10.24 big datavisualization
2013.10.24 big datavisualization
 
Detecting early-stage neurodegeneration using 3D ConvNet
Detecting early-stage neurodegeneration using 3D ConvNet Detecting early-stage neurodegeneration using 3D ConvNet
Detecting early-stage neurodegeneration using 3D ConvNet
 
Structured Forests for Fast Edge Detection [Paper Presentation]
Structured Forests for Fast Edge Detection [Paper Presentation]Structured Forests for Fast Edge Detection [Paper Presentation]
Structured Forests for Fast Edge Detection [Paper Presentation]
 
3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...
3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...
3D Brain Image Segmentation Model using Deep Learning and Hidden Markov Rando...
 
Clustering: A Scikit Learn Tutorial
Clustering: A Scikit Learn TutorialClustering: A Scikit Learn Tutorial
Clustering: A Scikit Learn Tutorial
 
Lecture 6 Basic Transform: Translation, Rotation, Scaling
Lecture 6 Basic Transform: Translation, Rotation, ScalingLecture 6 Basic Transform: Translation, Rotation, Scaling
Lecture 6 Basic Transform: Translation, Rotation, Scaling
 
Erik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better MortgageErik Bernhardsson, CTO, Better Mortgage
Erik Bernhardsson, CTO, Better Mortgage
 
Kmeans plusplus
Kmeans plusplusKmeans plusplus
Kmeans plusplus
 
Using parallel programming to improve performance of image processing
Using parallel programming to improve performance of image processingUsing parallel programming to improve performance of image processing
Using parallel programming to improve performance of image processing
 
Deep Learning for Computer Vision: Deep Networks (UPC 2016)
Deep Learning for Computer Vision: Deep Networks (UPC 2016)Deep Learning for Computer Vision: Deep Networks (UPC 2016)
Deep Learning for Computer Vision: Deep Networks (UPC 2016)
 
Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...
Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...
Hanie Sedghi, Research Scientist at Allen Institute for Artificial Intelligen...
 
Introduction to ml and dl
Introduction to ml and dlIntroduction to ml and dl
Introduction to ml and dl
 
Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems Non Deterministic and Deterministic Problems
Non Deterministic and Deterministic Problems
 
Deep Learning for Computer Vision: Visualization (UPC 2016)
Deep Learning for Computer Vision: Visualization (UPC 2016)Deep Learning for Computer Vision: Visualization (UPC 2016)
Deep Learning for Computer Vision: Visualization (UPC 2016)
 
Lecture32
Lecture32Lecture32
Lecture32
 
Rough K Means - Numerical Example
Rough K Means - Numerical ExampleRough K Means - Numerical Example
Rough K Means - Numerical Example
 
Knn
KnnKnn
Knn
 
Assignment 1
Assignment 1Assignment 1
Assignment 1
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
 

Similar to Deep Neural Network

Deep Residual Hashing Neural Network for Image Retrieval
Deep Residual Hashing Neural Network for Image RetrievalDeep Residual Hashing Neural Network for Image Retrieval
Deep Residual Hashing Neural Network for Image RetrievalEdwin Efraín Jiménez Lepe
 
Making BIG DATA smaller
Making BIG DATA smallerMaking BIG DATA smaller
Making BIG DATA smallerTony Tran
 
Lecture 5: Neural Networks II
Lecture 5: Neural Networks IILecture 5: Neural Networks II
Lecture 5: Neural Networks IISang Jun Lee
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionTe-Yen Liu
 
Oblivious Neural Network Predictions via MiniONN Transformations
Oblivious Neural Network Predictions via MiniONN TransformationsOblivious Neural Network Predictions via MiniONN Transformations
Oblivious Neural Network Predictions via MiniONN TransformationsSherif Abdelfattah
 
Neural Networks: Principal Component Analysis (PCA)
Neural Networks: Principal Component Analysis (PCA)Neural Networks: Principal Component Analysis (PCA)
Neural Networks: Principal Component Analysis (PCA)Mostafa G. M. Mostafa
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningCastLabKAIST
 
Deep learning with TensorFlow
Deep learning with TensorFlowDeep learning with TensorFlow
Deep learning with TensorFlowBarbara Fusinska
 
Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017Balázs Hidasi
 
Support vector machine
Support vector machineSupport vector machine
Support vector machinePrasenjit Dey
 
Machine Learning.pdf
Machine Learning.pdfMachine Learning.pdf
Machine Learning.pdfnikola_tesla1
 
Hands-on Tutorial of Deep Learning
Hands-on Tutorial of Deep LearningHands-on Tutorial of Deep Learning
Hands-on Tutorial of Deep LearningChun-Ming Chang
 
Paper Introduction "Density-aware person detection and tracking in crowds"
Paper Introduction "Density-aware person detection and tracking in crowds"Paper Introduction "Density-aware person detection and tracking in crowds"
Paper Introduction "Density-aware person detection and tracking in crowds"壮 八幡
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...Simplilearn
 
Learning a nonlinear embedding by preserving class neibourhood structure 최종
Learning a nonlinear embedding by preserving class neibourhood structure   최종Learning a nonlinear embedding by preserving class neibourhood structure   최종
Learning a nonlinear embedding by preserving class neibourhood structure 최종WooSung Choi
 
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017MLconf
 
Lesson_8_DeepLearning.pdf
Lesson_8_DeepLearning.pdfLesson_8_DeepLearning.pdf
Lesson_8_DeepLearning.pdfssuser7f0b19
 

Similar to Deep Neural Network (20)

Eye deep
Eye deepEye deep
Eye deep
 
Deep Residual Hashing Neural Network for Image Retrieval
Deep Residual Hashing Neural Network for Image RetrievalDeep Residual Hashing Neural Network for Image Retrieval
Deep Residual Hashing Neural Network for Image Retrieval
 
Making BIG DATA smaller
Making BIG DATA smallerMaking BIG DATA smaller
Making BIG DATA smaller
 
Lecture 5: Neural Networks II
Lecture 5: Neural Networks IILecture 5: Neural Networks II
Lecture 5: Neural Networks II
 
Machine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis IntroductionMachine Learning, Deep Learning and Data Analysis Introduction
Machine Learning, Deep Learning and Data Analysis Introduction
 
Oblivious Neural Network Predictions via MiniONN Transformations
Oblivious Neural Network Predictions via MiniONN TransformationsOblivious Neural Network Predictions via MiniONN Transformations
Oblivious Neural Network Predictions via MiniONN Transformations
 
Neural Networks: Principal Component Analysis (PCA)
Neural Networks: Principal Component Analysis (PCA)Neural Networks: Principal Component Analysis (PCA)
Neural Networks: Principal Component Analysis (PCA)
 
Hardware Acceleration for Machine Learning
Hardware Acceleration for Machine LearningHardware Acceleration for Machine Learning
Hardware Acceleration for Machine Learning
 
Deep learning with TensorFlow
Deep learning with TensorFlowDeep learning with TensorFlow
Deep learning with TensorFlow
 
Project PPT
Project PPTProject PPT
Project PPT
 
Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017Deep Learning in Recommender Systems - RecSys Summer School 2017
Deep Learning in Recommender Systems - RecSys Summer School 2017
 
Support vector machine
Support vector machineSupport vector machine
Support vector machine
 
Machine Learning.pdf
Machine Learning.pdfMachine Learning.pdf
Machine Learning.pdf
 
Hands-on Tutorial of Deep Learning
Hands-on Tutorial of Deep LearningHands-on Tutorial of Deep Learning
Hands-on Tutorial of Deep Learning
 
Paper Introduction "Density-aware person detection and tracking in crowds"
Paper Introduction "Density-aware person detection and tracking in crowds"Paper Introduction "Density-aware person detection and tracking in crowds"
Paper Introduction "Density-aware person detection and tracking in crowds"
 
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
What Is Deep Learning? | Introduction to Deep Learning | Deep Learning Tutori...
 
Learning a nonlinear embedding by preserving class neibourhood structure 최종
Learning a nonlinear embedding by preserving class neibourhood structure   최종Learning a nonlinear embedding by preserving class neibourhood structure   최종
Learning a nonlinear embedding by preserving class neibourhood structure 최종
 
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
Aaron Roth, Associate Professor, University of Pennsylvania, at MLconf NYC 2017
 
Cgm Lab Manual
Cgm Lab ManualCgm Lab Manual
Cgm Lab Manual
 
Lesson_8_DeepLearning.pdf
Lesson_8_DeepLearning.pdfLesson_8_DeepLearning.pdf
Lesson_8_DeepLearning.pdf
 

More from Jun Young Park

Introduction to PyTorch
Introduction to PyTorchIntroduction to PyTorch
Introduction to PyTorchJun Young Park
 
Using Multi GPU in PyTorch
Using Multi GPU in PyTorchUsing Multi GPU in PyTorch
Using Multi GPU in PyTorchJun Young Park
 
Trial for Practical NN Using
Trial for Practical NN UsingTrial for Practical NN Using
Trial for Practical NN UsingJun Young Park
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural NetworkJun Young Park
 
PyTorch and Transfer Learning
PyTorch and Transfer LearningPyTorch and Transfer Learning
PyTorch and Transfer LearningJun Young Park
 
Recurrent Neural Networks
Recurrent Neural NetworksRecurrent Neural Networks
Recurrent Neural NetworksJun Young Park
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural NetworkJun Young Park
 
GPU-Accelerated Parallel Computing
GPU-Accelerated Parallel ComputingGPU-Accelerated Parallel Computing
GPU-Accelerated Parallel ComputingJun Young Park
 

More from Jun Young Park (8)

Introduction to PyTorch
Introduction to PyTorchIntroduction to PyTorch
Introduction to PyTorch
 
Using Multi GPU in PyTorch
Using Multi GPU in PyTorchUsing Multi GPU in PyTorch
Using Multi GPU in PyTorch
 
Trial for Practical NN Using
Trial for Practical NN UsingTrial for Practical NN Using
Trial for Practical NN Using
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
 
PyTorch and Transfer Learning
PyTorch and Transfer LearningPyTorch and Transfer Learning
PyTorch and Transfer Learning
 
Recurrent Neural Networks
Recurrent Neural NetworksRecurrent Neural Networks
Recurrent Neural Networks
 
Introduction to Neural Network
Introduction to Neural NetworkIntroduction to Neural Network
Introduction to Neural Network
 
GPU-Accelerated Parallel Computing
GPU-Accelerated Parallel ComputingGPU-Accelerated Parallel Computing
GPU-Accelerated Parallel Computing
 

Recently uploaded

Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 

Recently uploaded (20)

Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 

Deep Neural Network

  • 1. Deep Neural Network RTSS JUN YOUNG PARK
  • 2. Reference ◦ R을 활용한 기계 학습 – Brett Lantz 著 ◦ 2017-1학기 ‘현대사회와 빅데이터‘ 교재 ◦ 데이터 전처리/표본 분석 과정 참조
  • 3. Number of Parameters From the last presentation … How many parameters in this linear model ? X W b S(Y)Y 0 1 0 0 0 Dog ! x Test data (Image) [1024x768] image 5 Classes 𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆 𝑊𝑊 + 𝑆𝑆𝑆𝑆𝑆𝑆𝑆𝑆 𝐵𝐵 = 𝐼𝐼 𝐼𝐼𝐼𝐼𝐼𝐼𝐼𝐼_𝑠𝑠𝑠𝑠𝑠𝑠𝑠𝑠 ∗ 𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶 + 𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶𝐶 = 3,932,165
  • 4. Go Deep & Wide ! W1 W2 W3 ? [784, 256] [256, 256] [256, 10] Hidden Layer [10]32 32 X Y Invisible from the input/output.
  • 5. Rectified Linear Units ◦ Why not Sigmoid ? ◦ Input signal may too near to 0 during back propagation. (Vanishing Gradient) 𝑅𝑅 𝑥𝑥 = � 𝑥𝑥, 𝑥𝑥 ≥ 0 0, 𝑥𝑥 < 0 𝜕𝜕 𝜕𝜕𝜕𝜕 {𝑅𝑅 𝑥𝑥 } = � 1, 𝑥𝑥 ≥ 0 0, 𝑥𝑥 < 0
  • 7. Weight Initialization ◦ DBN (Deep Belief Networks ) ◦ Process RBM for training each 2 layers ◦ After initialization -> We just need fine tuning(Training). ◦ Using Gaussian random number ◦ Xavier (2010) ◦ Divide Gaussian random number into number of inputs. ◦ He (2015) ◦ Divide the result of Xavier number into 2.
  • 8. L2 Regularization ◦ Large weight may bend the model. ◦ To avoid ‘Large Weight’, We use the term below ℒ = 1 𝑁𝑁 � 𝑖𝑖 𝐷𝐷 𝑆𝑆 𝑊𝑊𝑥𝑥𝑖𝑖 + 𝑏𝑏 , 𝐿𝐿𝑖𝑖 + 𝜆𝜆 � 𝑊𝑊2 0 ≤ 𝜆𝜆 ≤ 1 : Regularization strength
  • 9. Dropout ◦ Forces the network to have redundant representation While Testing : No Dropout While Training : Apply Dropout
  • 10. Chain Rule F GX Y y = 𝑔𝑔(𝑓𝑓 𝑥𝑥 ) FX G’ * y′ = 𝑔𝑔′ 𝑓𝑓 𝑥𝑥 ∗ 𝑓𝑓𝑓(𝑥𝑥) F’ X Y’ ◦ To make back propagation easier, We use operation graph like below.
  • 11. Back Propagation ◦ Get derivatives using ‘Back Propagation’ + 𝑥𝑥 𝑦𝑦 𝑧𝑧 𝑧𝑧 = 𝑥𝑥 + 𝑦𝑦 𝜕𝜕𝑧𝑧 𝜕𝜕𝜕𝜕 = 𝜕𝜕𝜕𝜕 𝜕𝜕𝑦𝑦 = 1 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 𝜕𝜕𝑧𝑧 𝜕𝜕𝜕𝜕 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 𝜕𝜕𝑧𝑧 𝜕𝜕𝑦𝑦 x 𝑥𝑥 𝑦𝑦 𝑧𝑧 𝑧𝑧 = 𝑥𝑥𝑥𝑥 𝜕𝜕𝑧𝑧 𝜕𝜕𝜕𝜕 = 𝑦𝑦, 𝜕𝜕𝜕𝜕 𝜕𝜕𝑦𝑦 = 𝑥𝑥 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 𝜕𝜕𝑧𝑧 𝜕𝜕𝜕𝜕 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 𝜕𝜕𝑧𝑧 𝜕𝜕𝑦𝑦 𝑦𝑦 � 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 𝑥𝑥 � 𝜕𝜕𝐿𝐿 𝜕𝜕𝑧𝑧 For signal 𝐿𝐿 …
  • 13. Practical Use ◦ Breast cancer diagnosis using ‘Deep Neural Network’ ◦ The example from the book ‘Machine Learning with R’ ◦ Using the dataset from ‘University of Wisconsin’ ◦ The dataset includes 32 features ◦ Diagnosis, Radius, Perimeter, Area … and so on
  • 14. Import/Define Methods ◦ Import packages for NumPy and TF ◦ Define the method for normalization 𝑧𝑧𝑛𝑛 = 𝑥𝑥𝑛𝑛 − min(𝒙𝒙) max 𝒙𝒙 − min(𝒙𝒙)
  • 15. Import Dataset ◦ Dataset from University of Wisconsin. ◦ Exclude unused feature (ID). ◦ Divide dataset for x and y.
  • 16. One-Hot Encoding ‘M’ [1, 0] [0, 1] Malignant Benign
  • 19. Build Session ◦ Can control forced/unforced. ◦ Restore previous trained weights. ◦ Write log for TensorBoard.
  • 20. Training Neurons ◦ 10001 steps per a run. ◦ Add summary for Tensorboard.
  • 21. Save Results and Get Accuracy ◦ Save previous training data to keep current weight and bias ◦ Each run trains 10001 times
  • 22. Result #1 <1st Attempt> <2nd Attempt>
  • 23. Attempt more … To use Xavier initializer
  • 24. Result #2 96.27% -> 97.01% 97.01% -> 97.76%
  • 25. Self Test ◦ 모델의 Parameter 수는 어떻게 결정되는지 설명하라. ◦ ReLU 함수의 개형과 그 미분의 결과는 어떻게 되는지 Sigmoid 함수와 비교하여 설명하라. ◦ Weight Initialization 의 목적과 그 방법을 설명하라. ◦ L2 Regularization 의 목적과 그 원리를 설명하라. ◦ Dropout 은 왜 필요한가 ? 또 훈련/시험시에 어떻게 설정해야 적절한가 ? ◦ NN 에 있어 Back Propagation 이 왜 유리한가? ◦ Ensemble Learning 에 대하여 설명하라.