SlideShare una empresa de Scribd logo
1 de 18
Descargar para leer sin conexión
Deep Generative Models
Mijung Kim
Discriminative vs. Generative Learning
Discriminative Learning Generative Learning
Learn 𝑝(𝑦|𝑥) directly Model 𝑝 𝑦 , 𝑝 𝑥 𝑦 first,
Then derive the posterior distribution:
𝑝 𝑦 𝑥 =
𝑝 𝑥 𝑦 𝑝(𝑦)
𝑝(𝑥)
2
Undirected Graph vs. Directed Graph
Undirected Directed
• Boltzmann Machines
• Restricted Boltzmann Machines
• Deep Boltzmann Machines
• Sigmoid Belief Networks
• Variational Autoencoders (VAE)
• Generative Adversarial Networks
(GAN)
3
a b
c
a b
c
Deep Belief
Networks
Boltzmann Machines
• Stochastic Recurrent Neural Network and Markov Random
Field invented by Hinton and Sejnowski in 1985
• 𝑷 𝒙 =
𝐞𝐱𝐩(−𝑬 𝒙 )
𝒁
> E(x): Energy function
> Z: partition function where σ 𝑥 𝑃 𝑥 = 1
• Energy-based model: positive values all the time
• Single visible layer and single hidden layer
• Fully connected: not practical to implement
4
Restricted Boltzmann Machines
• Dimensionality reduction, classification, regression,
collaborative filtering, feature learning and topic modeling
• 𝑷 𝐯 = 𝒗, 𝐡 = 𝒉 =
𝟏
𝒁
𝐞𝐱𝐩(−𝑬 𝒗, 𝒉 )
• Two layers like BMs
• Building blocks of deep probabilistic models
• Gibbs sampling with Contrastive Divergence (CD) or Persistent
CD
5
Comparison btw BMs and RBMs
Boltzmann Machines Restricted Boltzmann Machines
v1 v2 v3
h1 h2 h3 h4
v1 v2 v3
h1 h2 h3 h4
6
𝑬 𝒗, 𝒉 = −𝒗 𝑻
𝑹𝒗 − 𝒉 𝑻
𝑺𝒉 − 𝒗 𝑻
𝑾𝒉 − 𝒃 𝑻
𝒗 − 𝒄 𝑻
𝒉 𝑬 𝒗, 𝒉 = −𝒃 𝑻
𝒗 − 𝒄 𝑻
𝒉 − 𝒗 𝑻
𝑾𝒉
Deep Belief
Networks
• Unsupervised
• Small dataset
• Stacked RBMs
• Pre-train each RBM
• Undirected + Directed
7
RBM
Sigmoid
Belief
Net
• 𝑃 v, h1, h2, h3 =
𝑃 v h1 𝑃 h1 h2 𝑃(h2, h3)
• 𝑃 v h1 = ς𝑖 𝑃(𝑣𝑖|h1)
• 𝑃 h1
h2
= ς 𝑗 𝑃(ℎ𝑗
1
|h2
)
• 𝑃 h2
, h3
=
1
𝑍(𝑊3)
exp(h2𝑇
𝑊3
h3
)
8
RBM
Sigmoid
Belief
Net
ℎ1
ℎ2
ℎ3
v
𝑊3
𝑊2
𝑊1
Sigmoid Belief Net RBM
Limitations of DBN (By Ruslan Salakhutdinov)
• Explaining away
• Greedy layer-wise pre-training
> no optimization over all layers
• Approximation inference is feed-forward
> no bottom-up and top-down
9
http://www.slideshare.net/zukun/p05-deep-boltzmann-machines-cvpr2012-deep-learning-methods-for-vision
Deep Boltzmann
Machines
• Unsupervised
• Small dataset
• Stacked RBMs
• Pre-train each RBM
• Undirected
10
• 𝑃 𝜃 v =
1
𝑍(𝜃)
σh1,h2,h3 exp( v 𝑇 𝑊1h1 +
h1𝑇 𝑊2h2 + h2𝑇 𝑊3h3)
• 𝜃 = {𝑊1, 𝑊2, 𝑊3}
• Bottom-up and Top-down:
• 𝑃 ℎ𝑗
2
= 1|h1, h3 =
𝜎(σ 𝒌 𝑾 𝒌𝒋
𝟑
𝒉 𝒌
𝟑
+ σ 𝒎 𝑾 𝒎𝒋
𝟐
𝒉 𝒎
𝟏 )
11
ℎ1
ℎ2
ℎ3
v
𝑊3
𝑊2
𝑊1
Variational Autoencoders (VAE)
12
Encoder Decoderx x’
μ
σ
Z
𝑞(𝑧|𝑥) 𝑝(𝑥|𝑧)
Sampling Reconstruct
ℒ 𝑞 = −𝑫 𝑲𝑳 𝒒 𝒛 𝒙 ∥ 𝒑 𝒎𝒐𝒅𝒆𝒍 𝒛 + 𝔼 𝒛~𝒒 𝒛 𝒙 𝐥𝐨𝐠 𝒑 𝒎𝒐𝒅𝒆𝒍(𝒙|𝒛)
𝔃 ~ 𝓝(𝝁, 𝝈)
http://www.slideshare.net/KazukiNitta/variational-autoencoder-68705109
Stochastic Gradient Variational Bayes
(SGVB) Estimator
13
Encoder Decoderx x’
μ
σ
Z
Back Prop.
Feed Forward
𝝐 ~ 𝓝 𝟎, 𝑰
𝔃 = 𝝁 + 𝝐𝝈
14http://dpkingma.com/wordpress/wp-content/uploads/2014/05/2014-03_talk_iclr.pdf
Generative Adversarial Networks(GAN)
15
Data Sample Discriminator
Generator
Sample
Noise
Yes or No
Generator
https://ishmaelbelghazi.github.io/ALI
Convolutional Neural Networks
16
Image Classification
Deep Convolutional Generative
Adversarial Networks (DCGAN)
17
https://openai.com/blog/generative-models/
Real Images vs. Generated images
18
http://kenkihara.com/projects/GAN.html

Más contenido relacionado

La actualidad más candente

Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks남주 김
 
Intro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksIntro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksMark Scully
 
Support vector machines (svm)
Support vector machines (svm)Support vector machines (svm)
Support vector machines (svm)Sharayu Patil
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNNAshray Bhandare
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational AutoencoderMark Chang
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep LearningOswald Campesato
 
오토인코더의 모든 것
오토인코더의 모든 것오토인코더의 모든 것
오토인코더의 모든 것NAVER Engineering
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkYan Xu
 
Neural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronNeural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronMostafa G. M. Mostafa
 
INTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRUINTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRUSri Geetha
 
Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...
Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...
Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...Edureka!
 
Understanding Bagging and Boosting
Understanding Bagging and BoostingUnderstanding Bagging and Boosting
Understanding Bagging and BoostingMohit Rajput
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep LearningPoo Kuan Hoong
 
Deep Belief Networks
Deep Belief NetworksDeep Belief Networks
Deep Belief NetworksHasan H Topcu
 
Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...
Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...
Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...Edureka!
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetSungminYou
 

La actualidad más candente (20)

Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
Intro To Convolutional Neural Networks
Intro To Convolutional Neural NetworksIntro To Convolutional Neural Networks
Intro To Convolutional Neural Networks
 
Support vector machines (svm)
Support vector machines (svm)Support vector machines (svm)
Support vector machines (svm)
 
Deep Learning - CNN and RNN
Deep Learning - CNN and RNNDeep Learning - CNN and RNN
Deep Learning - CNN and RNN
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
 
Introduction to Deep Learning
Introduction to Deep LearningIntroduction to Deep Learning
Introduction to Deep Learning
 
Introduction to Deep learning
Introduction to Deep learningIntroduction to Deep learning
Introduction to Deep learning
 
Transfer Learning
Transfer LearningTransfer Learning
Transfer Learning
 
오토인코더의 모든 것
오토인코더의 모든 것오토인코더의 모든 것
오토인코더의 모든 것
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
Neural Networks: Multilayer Perceptron
Neural Networks: Multilayer PerceptronNeural Networks: Multilayer Perceptron
Neural Networks: Multilayer Perceptron
 
Deep learning
Deep learningDeep learning
Deep learning
 
Support vector machine
Support vector machineSupport vector machine
Support vector machine
 
INTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRUINTRODUCTION TO NLP, RNN, LSTM, GRU
INTRODUCTION TO NLP, RNN, LSTM, GRU
 
Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...
Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...
Recurrent Neural Networks (RNN) | RNN LSTM | Deep Learning Tutorial | Tensorf...
 
Understanding Bagging and Boosting
Understanding Bagging and BoostingUnderstanding Bagging and Boosting
Understanding Bagging and Boosting
 
An Introduction to Deep Learning
An Introduction to Deep LearningAn Introduction to Deep Learning
An Introduction to Deep Learning
 
Deep Belief Networks
Deep Belief NetworksDeep Belief Networks
Deep Belief Networks
 
Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...
Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...
Restricted Boltzmann Machine | Neural Network Tutorial | Deep Learning Tutori...
 
Convolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNet
 

Destacado

VAE-type Deep Generative Models
VAE-type Deep Generative ModelsVAE-type Deep Generative Models
VAE-type Deep Generative ModelsKenta Oono
 
machine learning and art hack day
machine learning and art hack daymachine learning and art hack day
machine learning and art hack dayjtoy
 
Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)
Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)
Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)Ohsawa Goodfellow
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer VisionDavid Dao
 
Lukáš Vrábel - Deep Convolutional Neural Networks
Lukáš Vrábel - Deep Convolutional Neural NetworksLukáš Vrábel - Deep Convolutional Neural Networks
Lukáš Vrábel - Deep Convolutional Neural NetworksMachine Learning Prague
 
Deep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image GenerationDeep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image GenerationTJ Torres
 
Deep Advances in Generative Modeling
Deep Advances in Generative ModelingDeep Advances in Generative Modeling
Deep Advances in Generative Modelingindico data
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakPyData
 
Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature surveyAkshay Hegde
 
Variational AutoEncoder
Variational AutoEncoderVariational AutoEncoder
Variational AutoEncoderKazuki Nitta
 
Tokyo Webmining Talk1
Tokyo Webmining Talk1Tokyo Webmining Talk1
Tokyo Webmining Talk1Kenta Oono
 
猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoderSho Tatsuno
 
情報幾何学の基礎、第7章発表ノート
情報幾何学の基礎、第7章発表ノート情報幾何学の基礎、第7章発表ノート
情報幾何学の基礎、第7章発表ノートKenta Oono
 

Destacado (13)

VAE-type Deep Generative Models
VAE-type Deep Generative ModelsVAE-type Deep Generative Models
VAE-type Deep Generative Models
 
machine learning and art hack day
machine learning and art hack daymachine learning and art hack day
machine learning and art hack day
 
Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)
Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)
Deep Learning via Semi-Supervised Embedding (第 7 回 Deep Learning 勉強会資料; 大澤)
 
Deep learning in Computer Vision
Deep learning in Computer VisionDeep learning in Computer Vision
Deep learning in Computer Vision
 
Lukáš Vrábel - Deep Convolutional Neural Networks
Lukáš Vrábel - Deep Convolutional Neural NetworksLukáš Vrábel - Deep Convolutional Neural Networks
Lukáš Vrábel - Deep Convolutional Neural Networks
 
Deep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image GenerationDeep Style: Using Variational Auto-encoders for Image Generation
Deep Style: Using Variational Auto-encoders for Image Generation
 
Deep Advances in Generative Modeling
Deep Advances in Generative ModelingDeep Advances in Generative Modeling
Deep Advances in Generative Modeling
 
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr TeterwakLearn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
Learn to Build an App to Find Similar Images using Deep Learning- Piotr Teterwak
 
Deep Learning - A Literature survey
Deep Learning - A Literature surveyDeep Learning - A Literature survey
Deep Learning - A Literature survey
 
Variational AutoEncoder
Variational AutoEncoderVariational AutoEncoder
Variational AutoEncoder
 
Tokyo Webmining Talk1
Tokyo Webmining Talk1Tokyo Webmining Talk1
Tokyo Webmining Talk1
 
猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder
 
情報幾何学の基礎、第7章発表ノート
情報幾何学の基礎、第7章発表ノート情報幾何学の基礎、第7章発表ノート
情報幾何学の基礎、第7章発表ノート
 

Similar a Deep Generative Models

Exploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation LearningExploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation LearningSungchul Kim
 
PR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningPR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningSungchul Kim
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooJaeJun Yoo
 
201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture Search201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture SearchDaeJin Kim
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
 
Graph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear AlgebraGraph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear AlgebraJason Riedy
 
generalized_nbody_acs_2015_challacombe
generalized_nbody_acs_2015_challacombegeneralized_nbody_acs_2015_challacombe
generalized_nbody_acs_2015_challacombeMatt Challacombe
 
4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalization4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalizationDonghoon Park
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learningJunaid Bhat
 
High performance large-scale image recognition without normalization
High performance large-scale image recognition without normalizationHigh performance large-scale image recognition without normalization
High performance large-scale image recognition without normalizationtaeseon ryu
 
Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...
Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...
Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...Lucidworks
 
Dueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learningDueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learningTaehoon Kim
 
Principles of soft computing-Associative memory networks
Principles of soft computing-Associative memory networksPrinciples of soft computing-Associative memory networks
Principles of soft computing-Associative memory networksSivagowry Shathesh
 
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...ssuser4b1f48
 

Similar a Deep Generative Models (20)

convolutional_rbm.ppt
convolutional_rbm.pptconvolutional_rbm.ppt
convolutional_rbm.ppt
 
Exploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation LearningExploring Simple Siamese Representation Learning
Exploring Simple Siamese Representation Learning
 
PR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation LearningPR-305: Exploring Simple Siamese Representation Learning
PR-305: Exploring Simple Siamese Representation Learning
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun Yoo
 
201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture Search201907 AutoML and Neural Architecture Search
201907 AutoML and Neural Architecture Search
 
230727_HB_JointJournalClub.pptx
230727_HB_JointJournalClub.pptx230727_HB_JointJournalClub.pptx
230727_HB_JointJournalClub.pptx
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
Graph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear AlgebraGraph Analysis Beyond Linear Algebra
Graph Analysis Beyond Linear Algebra
 
gan.pdf
gan.pdfgan.pdf
gan.pdf
 
generalized_nbody_acs_2015_challacombe
generalized_nbody_acs_2015_challacombegeneralized_nbody_acs_2015_challacombe
generalized_nbody_acs_2015_challacombe
 
4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalization4 high performance large-scale image recognition without normalization
4 high performance large-scale image recognition without normalization
 
Introduction to deep learning
Introduction to deep learningIntroduction to deep learning
Introduction to deep learning
 
K-means and GMM
K-means and GMMK-means and GMM
K-means and GMM
 
High performance large-scale image recognition without normalization
High performance large-scale image recognition without normalizationHigh performance large-scale image recognition without normalization
High performance large-scale image recognition without normalization
 
Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...
Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...
Image-Based E-Commerce Product Discovery: A Deep Learning Case Study - Denis ...
 
Iiwas19 yamazaki slide
Iiwas19 yamazaki slideIiwas19 yamazaki slide
Iiwas19 yamazaki slide
 
Dueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learningDueling network architectures for deep reinforcement learning
Dueling network architectures for deep reinforcement learning
 
Principles of soft computing-Associative memory networks
Principles of soft computing-Associative memory networksPrinciples of soft computing-Associative memory networks
Principles of soft computing-Associative memory networks
 
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...NS-CUK Seminar: H.B.Kim,  Review on "Sequential Recommendation with Graph Neu...
NS-CUK Seminar: H.B.Kim, Review on "Sequential Recommendation with Graph Neu...
 

Último

SR-101-01012024-EN.docx Federal Constitution of the Swiss Confederation
SR-101-01012024-EN.docx  Federal Constitution  of the Swiss ConfederationSR-101-01012024-EN.docx  Federal Constitution  of the Swiss Confederation
SR-101-01012024-EN.docx Federal Constitution of the Swiss ConfederationEfruzAsilolu
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...nirzagarg
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...gajnagarg
 
Gartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxGartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxchadhar227
 
Data Analyst Tasks to do the internship.pdf
Data Analyst Tasks to do the internship.pdfData Analyst Tasks to do the internship.pdf
Data Analyst Tasks to do the internship.pdftheeltifs
 
7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.pptibrahimabdi22
 
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptxThe-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptxVivek487417
 
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...nirzagarg
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...gajnagarg
 
怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制
怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制
怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制vexqp
 
Harnessing the Power of GenAI for BI and Reporting.pptx
Harnessing the Power of GenAI for BI and Reporting.pptxHarnessing the Power of GenAI for BI and Reporting.pptx
Harnessing the Power of GenAI for BI and Reporting.pptxParas Gupta
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Valters Lauzums
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样wsppdmt
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制vexqp
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...nirzagarg
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...Bertram Ludäscher
 
Switzerland Constitution 2002.pdf.........
Switzerland Constitution 2002.pdf.........Switzerland Constitution 2002.pdf.........
Switzerland Constitution 2002.pdf.........EfruzAsilolu
 
一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格
一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格
一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格q6pzkpark
 

Último (20)

SR-101-01012024-EN.docx Federal Constitution of the Swiss Confederation
SR-101-01012024-EN.docx  Federal Constitution  of the Swiss ConfederationSR-101-01012024-EN.docx  Federal Constitution  of the Swiss Confederation
SR-101-01012024-EN.docx Federal Constitution of the Swiss Confederation
 
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
Top profile Call Girls In Tumkur [ 7014168258 ] Call Me For Genuine Models We...
 
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In bhavnagar [ 7014168258 ] Call Me For Genuine Models...
 
Gartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptxGartner's Data Analytics Maturity Model.pptx
Gartner's Data Analytics Maturity Model.pptx
 
Data Analyst Tasks to do the internship.pdf
Data Analyst Tasks to do the internship.pdfData Analyst Tasks to do the internship.pdf
Data Analyst Tasks to do the internship.pdf
 
7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt7. Epi of Chronic respiratory diseases.ppt
7. Epi of Chronic respiratory diseases.ppt
 
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptxThe-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
The-boAt-Story-Navigating-the-Waves-of-Innovation.pptx
 
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
Top profile Call Girls In Begusarai [ 7014168258 ] Call Me For Genuine Models...
 
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
Top profile Call Girls In Vadodara [ 7014168258 ] Call Me For Genuine Models ...
 
怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制
怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制
怎样办理伦敦大学毕业证(UoL毕业证书)成绩单学校原版复制
 
Abortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get CytotecAbortion pills in Jeddah | +966572737505 | Get Cytotec
Abortion pills in Jeddah | +966572737505 | Get Cytotec
 
Harnessing the Power of GenAI for BI and Reporting.pptx
Harnessing the Power of GenAI for BI and Reporting.pptxHarnessing the Power of GenAI for BI and Reporting.pptx
Harnessing the Power of GenAI for BI and Reporting.pptx
 
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
Digital Advertising Lecture for Advanced Digital & Social Media Strategy at U...
 
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
如何办理英国诺森比亚大学毕业证(NU毕业证书)成绩单原件一模一样
 
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
 
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
怎样办理圣地亚哥州立大学毕业证(SDSU毕业证书)成绩单学校原版复制
 
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
Top profile Call Girls In Bihar Sharif [ 7014168258 ] Call Me For Genuine Mod...
 
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...Reconciling Conflicting Data Curation Actions:  Transparency Through Argument...
Reconciling Conflicting Data Curation Actions: Transparency Through Argument...
 
Switzerland Constitution 2002.pdf.........
Switzerland Constitution 2002.pdf.........Switzerland Constitution 2002.pdf.........
Switzerland Constitution 2002.pdf.........
 
一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格
一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格
一比一原版(曼大毕业证书)曼尼托巴大学毕业证成绩单留信学历认证一手价格
 

Deep Generative Models

  • 2. Discriminative vs. Generative Learning Discriminative Learning Generative Learning Learn 𝑝(𝑦|𝑥) directly Model 𝑝 𝑦 , 𝑝 𝑥 𝑦 first, Then derive the posterior distribution: 𝑝 𝑦 𝑥 = 𝑝 𝑥 𝑦 𝑝(𝑦) 𝑝(𝑥) 2
  • 3. Undirected Graph vs. Directed Graph Undirected Directed • Boltzmann Machines • Restricted Boltzmann Machines • Deep Boltzmann Machines • Sigmoid Belief Networks • Variational Autoencoders (VAE) • Generative Adversarial Networks (GAN) 3 a b c a b c Deep Belief Networks
  • 4. Boltzmann Machines • Stochastic Recurrent Neural Network and Markov Random Field invented by Hinton and Sejnowski in 1985 • 𝑷 𝒙 = 𝐞𝐱𝐩(−𝑬 𝒙 ) 𝒁 > E(x): Energy function > Z: partition function where σ 𝑥 𝑃 𝑥 = 1 • Energy-based model: positive values all the time • Single visible layer and single hidden layer • Fully connected: not practical to implement 4
  • 5. Restricted Boltzmann Machines • Dimensionality reduction, classification, regression, collaborative filtering, feature learning and topic modeling • 𝑷 𝐯 = 𝒗, 𝐡 = 𝒉 = 𝟏 𝒁 𝐞𝐱𝐩(−𝑬 𝒗, 𝒉 ) • Two layers like BMs • Building blocks of deep probabilistic models • Gibbs sampling with Contrastive Divergence (CD) or Persistent CD 5
  • 6. Comparison btw BMs and RBMs Boltzmann Machines Restricted Boltzmann Machines v1 v2 v3 h1 h2 h3 h4 v1 v2 v3 h1 h2 h3 h4 6 𝑬 𝒗, 𝒉 = −𝒗 𝑻 𝑹𝒗 − 𝒉 𝑻 𝑺𝒉 − 𝒗 𝑻 𝑾𝒉 − 𝒃 𝑻 𝒗 − 𝒄 𝑻 𝒉 𝑬 𝒗, 𝒉 = −𝒃 𝑻 𝒗 − 𝒄 𝑻 𝒉 − 𝒗 𝑻 𝑾𝒉
  • 7. Deep Belief Networks • Unsupervised • Small dataset • Stacked RBMs • Pre-train each RBM • Undirected + Directed 7 RBM Sigmoid Belief Net
  • 8. • 𝑃 v, h1, h2, h3 = 𝑃 v h1 𝑃 h1 h2 𝑃(h2, h3) • 𝑃 v h1 = ς𝑖 𝑃(𝑣𝑖|h1) • 𝑃 h1 h2 = ς 𝑗 𝑃(ℎ𝑗 1 |h2 ) • 𝑃 h2 , h3 = 1 𝑍(𝑊3) exp(h2𝑇 𝑊3 h3 ) 8 RBM Sigmoid Belief Net ℎ1 ℎ2 ℎ3 v 𝑊3 𝑊2 𝑊1 Sigmoid Belief Net RBM
  • 9. Limitations of DBN (By Ruslan Salakhutdinov) • Explaining away • Greedy layer-wise pre-training > no optimization over all layers • Approximation inference is feed-forward > no bottom-up and top-down 9 http://www.slideshare.net/zukun/p05-deep-boltzmann-machines-cvpr2012-deep-learning-methods-for-vision
  • 10. Deep Boltzmann Machines • Unsupervised • Small dataset • Stacked RBMs • Pre-train each RBM • Undirected 10
  • 11. • 𝑃 𝜃 v = 1 𝑍(𝜃) σh1,h2,h3 exp( v 𝑇 𝑊1h1 + h1𝑇 𝑊2h2 + h2𝑇 𝑊3h3) • 𝜃 = {𝑊1, 𝑊2, 𝑊3} • Bottom-up and Top-down: • 𝑃 ℎ𝑗 2 = 1|h1, h3 = 𝜎(σ 𝒌 𝑾 𝒌𝒋 𝟑 𝒉 𝒌 𝟑 + σ 𝒎 𝑾 𝒎𝒋 𝟐 𝒉 𝒎 𝟏 ) 11 ℎ1 ℎ2 ℎ3 v 𝑊3 𝑊2 𝑊1
  • 12. Variational Autoencoders (VAE) 12 Encoder Decoderx x’ μ σ Z 𝑞(𝑧|𝑥) 𝑝(𝑥|𝑧) Sampling Reconstruct ℒ 𝑞 = −𝑫 𝑲𝑳 𝒒 𝒛 𝒙 ∥ 𝒑 𝒎𝒐𝒅𝒆𝒍 𝒛 + 𝔼 𝒛~𝒒 𝒛 𝒙 𝐥𝐨𝐠 𝒑 𝒎𝒐𝒅𝒆𝒍(𝒙|𝒛) 𝔃 ~ 𝓝(𝝁, 𝝈) http://www.slideshare.net/KazukiNitta/variational-autoencoder-68705109
  • 13. Stochastic Gradient Variational Bayes (SGVB) Estimator 13 Encoder Decoderx x’ μ σ Z Back Prop. Feed Forward 𝝐 ~ 𝓝 𝟎, 𝑰 𝔃 = 𝝁 + 𝝐𝝈
  • 15. Generative Adversarial Networks(GAN) 15 Data Sample Discriminator Generator Sample Noise Yes or No Generator https://ishmaelbelghazi.github.io/ALI
  • 17. Deep Convolutional Generative Adversarial Networks (DCGAN) 17 https://openai.com/blog/generative-models/
  • 18. Real Images vs. Generated images 18 http://kenkihara.com/projects/GAN.html