SlideShare ist ein Scribd-Unternehmen logo
1 von 16
Downloaden Sie, um offline zu lesen
Auto-Encoding Variational Bayes
Diederik P. Kingma, Max Welling
Machine Learning Group Universiteit van Amsterdam
ICLR 2014 conference submission, Cited by 4655
May 23, 2019
SMC AI Research Center
Kyuri Kim
Introduction
1.1 Supervised learning vs. Unsupervised learning
Supervised learning Ex. Classification
Regression
Object Detection
Semantic Segmentation
Image captioning
:
Data: (x, y)
x is data, y is label
Learn a function to map x → y
Unsupervised learning
Ex. Clustering
Dimensionality Reduction
Density estimation
Feature Learning
:
Data: (x)
Just data, no label
Learn something underlying
hidden structure of the data
1-d Density estimation 2-d Density estimation
Ex.
Image Detection
Ex.
2
Introduction
1.2 Auto Encoder (Feature Learning)
1. Unsupervised Learning
2. ML density estimation
3. Manifold Learning
4. Generative model learning
In Auto Encoder Training:
In Trained Auto Encoder :
Encoding Decoding
Latent Variable
𝝌 𝒙
L (𝝌, 𝒚)
Reconstruction Error
Decoder는 최소한의 학습 데이터는 생성해 낼 수 있고,
Encoder는 최소한의 학습 데이터는 latent vector로 표현할 수 있다.
Minimize
𝒁
3
𝑥)
Introduction
1.3 Generative Model
Given training data, generate new samples from same distribution
Ex. Variational Auto encoders (VAE), Generative Adversarial Network(GAN)
Generated samples ~ 𝑝 𝑚𝑜𝑑𝑒𝑙(𝑥)Training data ~ 𝑝 𝑑𝑎𝑡𝑎(𝑥)
Want to learn 𝒑 𝒎𝒐𝒅𝒆𝒍 𝒙 similar to ~ 𝒑 𝒅𝒂𝒕𝒂(𝒙)
Probability density function
4
Introduction
1.4 Generative Model Network
Generative model taxonomy
Ian Goodfellow, "NIPS 2016 Tutorial: Generative Adversarial Networks"
5
Experiments
2.1 Variational Auto-Encoder
Target Data
𝝌
Latent Variable
𝑧
P(𝑥|𝑧)P(𝑧)
Sample from true prior Sample from true conditional
Decoder Network
How to Train the Model?
6
Maximum likelihood
estimation
Experiments
2.2 Variation Inference
Variation InferenceTarget Data
Generator
𝒈 𝜽(.)
𝝌
Latent Variable
𝑝 (𝑧|𝑥) ≈ 𝑞 𝜙(𝑧|𝑥)~𝑧
sampling 𝑧 from 𝑝(𝑧|𝑥)
Z를 정규분포에서 Sampling하는 것 보다 x와 유의미하게 Sample이 나올 수 있는 확률 분포 𝑝(𝑧|𝑥)로부터
Sampling. 그러나 𝑝(𝑧|𝑥)가 무엇인지 알지 못하므로, 우리가 알고 있는 확률분포 중 하나를 택하여 𝑞 𝜙(𝑧|𝑥)
그것의 parameter 값을 조정, 𝑝(𝑧|𝑥)과 유사하게 만든다.
7
𝑧
Experiments
2.3 Variational Auto-Encoder
(1) Definition of VAE
Variational Inference를 Auto Encoder의 구조를 통해 구현한 Generate Model.
(2) Structure of VAE When z is deterministic value
On the respects of probability
Where z is in a distribution
X가 주어졌을 때 z의 확률 Variational Inference
𝑧
𝒈 𝜽(.)𝒒∅(.)
𝝌𝝌
𝑝(𝑧|𝑥) ≈ 𝑝(𝑧)
8
Experiments
2.4 ELBO(Evidence Lower Bound)
ELBO(Evidence Lower Bound)
Variational
Inference
Jensen’s Inequality
9
Experiments
2.4 ELBO(Evidence Lower Bound)
ELBO(Evidence Lower Bound) KL term
두 확률분포 간의 거리 ≥ 0 10
Experiments
2.4 ELBO(Evidence Lower Bound)
KL term
①
③
②
11
Experiments
2.4 ELBO(Evidence Lower Bound)
𝒈 𝜽(𝒙|𝒛)𝒒∅(𝒛|𝒙)
Encoder
Inference Network
Decoder
Generation Network
sampling
Reconstruction error Regularization
12
Experiments
2.5 Reparameterization trick
mean
Reconstruction
error
sampling
Backpropagation Impossible → Reparameterization trick
13
Experiments
2.5 Reparameterization trick
정규분포
14
Result & Conclusion
http://dpkingma.com/sgvb_mnist_demo/demo.html
Z1
Degree of smile
Z2
Head pose
Z1
Z2
15
Appendix
- Auto Encoder “어떤 방식으로 pre train하였는가?”
16

Weitere ähnliche Inhalte

Was ist angesagt?

[AIoTLab]attention mechanism.pptx
[AIoTLab]attention mechanism.pptx[AIoTLab]attention mechanism.pptx
[AIoTLab]attention mechanism.pptxTuCaoMinh2
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNNShuai Zhang
 
Transfer learning-presentation
Transfer learning-presentationTransfer learning-presentation
Transfer learning-presentationBushra Jbawi
 
Autoencoder
AutoencoderAutoencoder
AutoencoderHARISH R
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural NetworksPyData
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
Machine Learning lecture6(regularization)
Machine Learning lecture6(regularization)Machine Learning lecture6(regularization)
Machine Learning lecture6(regularization)cairo university
 
Domain Adaptation
Domain AdaptationDomain Adaptation
Domain AdaptationMark Chang
 
Autoencoders in Deep Learning
Autoencoders in Deep LearningAutoencoders in Deep Learning
Autoencoders in Deep Learningmilad abbasi
 
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Gaurav Mittal
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial NetworksMustafa Yagmur
 
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
PR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic ModelsPR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic ModelsHyeongmin Lee
 
Anomaly/Novelty detection with scikit-learn
Anomaly/Novelty detection with scikit-learnAnomaly/Novelty detection with scikit-learn
Anomaly/Novelty detection with scikit-learnagramfort
 
210523 swin transformer v1.5
210523 swin transformer v1.5210523 swin transformer v1.5
210523 swin transformer v1.5taeseon ryu
 
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...준식 최
 

Was ist angesagt? (20)

[AIoTLab]attention mechanism.pptx
[AIoTLab]attention mechanism.pptx[AIoTLab]attention mechanism.pptx
[AIoTLab]attention mechanism.pptx
 
Introduction to CNN
Introduction to CNNIntroduction to CNN
Introduction to CNN
 
Transfer learning-presentation
Transfer learning-presentationTransfer learning-presentation
Transfer learning-presentation
 
Autoencoder
AutoencoderAutoencoder
Autoencoder
 
Transfer Learning and Fine-tuning Deep Neural Networks
 Transfer Learning and Fine-tuning Deep Neural Networks Transfer Learning and Fine-tuning Deep Neural Networks
Transfer Learning and Fine-tuning Deep Neural Networks
 
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
Transfer Learning and Domain Adaptation - Ramon Morros - UPC Barcelona 2018
 
Transfer Learning
Transfer LearningTransfer Learning
Transfer Learning
 
Machine Learning lecture6(regularization)
Machine Learning lecture6(regularization)Machine Learning lecture6(regularization)
Machine Learning lecture6(regularization)
 
Domain Adaptation
Domain AdaptationDomain Adaptation
Domain Adaptation
 
Autoencoders in Deep Learning
Autoencoders in Deep LearningAutoencoders in Deep Learning
Autoencoders in Deep Learning
 
Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)Convolutional Neural Networks (CNN)
Convolutional Neural Networks (CNN)
 
U-Net (1).pptx
U-Net (1).pptxU-Net (1).pptx
U-Net (1).pptx
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial Networks
 
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
Loss Functions for Deep Learning - Javier Ruiz Hidalgo - UPC Barcelona 2018
 
Deep learning ppt
Deep learning pptDeep learning ppt
Deep learning ppt
 
PR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic ModelsPR-409: Denoising Diffusion Probabilistic Models
PR-409: Denoising Diffusion Probabilistic Models
 
Anomaly/Novelty detection with scikit-learn
Anomaly/Novelty detection with scikit-learnAnomaly/Novelty detection with scikit-learn
Anomaly/Novelty detection with scikit-learn
 
CNN Tutorial
CNN TutorialCNN Tutorial
CNN Tutorial
 
210523 swin transformer v1.5
210523 swin transformer v1.5210523 swin transformer v1.5
210523 swin transformer v1.5
 
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
Paper Summary of Beta-VAE: Learning Basic Visual Concepts with a Constrained ...
 

Ähnlich wie Auto-encoding variational bayes

Visualizing the Model Selection Process
Visualizing the Model Selection ProcessVisualizing the Model Selection Process
Visualizing the Model Selection ProcessBenjamin Bengfort
 
A simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsA simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsDevansh16
 
Software tookits for machine learning and graphical models
Software tookits for machine learning and graphical modelsSoftware tookits for machine learning and graphical models
Software tookits for machine learning and graphical modelsbutest
 
Camp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine LearningCamp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine LearningKrzysztof Kowalczyk
 
Deep image generating models
Deep image generating modelsDeep image generating models
Deep image generating modelsLuba Elliott
 
FUNCTION APPROXIMATION
FUNCTION APPROXIMATIONFUNCTION APPROXIMATION
FUNCTION APPROXIMATIONankita pandey
 
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxRMDAcademicCoordinat
 
imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdfKammetaJoshna
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
 
[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare Events[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare EventsTaegyun Jeon
 
Machine Learning Live
Machine Learning LiveMachine Learning Live
Machine Learning LiveMike Anderson
 
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Daniel Lewis
 
Variational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math BehindVariational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math BehindVarun Reddy
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
 
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...IJNSA Journal
 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...butest
 
Citython presentation
Citython presentationCitython presentation
Citython presentationAnkit Tewari
 

Ähnlich wie Auto-encoding variational bayes (20)

Visualizing the Model Selection Process
Visualizing the Model Selection ProcessVisualizing the Model Selection Process
Visualizing the Model Selection Process
 
A simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representationsA simple framework for contrastive learning of visual representations
A simple framework for contrastive learning of visual representations
 
Software tookits for machine learning and graphical models
Software tookits for machine learning and graphical modelsSoftware tookits for machine learning and graphical models
Software tookits for machine learning and graphical models
 
Camp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine LearningCamp IT: Making the World More Efficient Using AI & Machine Learning
Camp IT: Making the World More Efficient Using AI & Machine Learning
 
Deep image generating models
Deep image generating modelsDeep image generating models
Deep image generating models
 
FUNCTION APPROXIMATION
FUNCTION APPROXIMATIONFUNCTION APPROXIMATION
FUNCTION APPROXIMATION
 
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptxGAN Deep Learning Approaches to Image Processing Applications (1).pptx
GAN Deep Learning Approaches to Image Processing Applications (1).pptx
 
imageclassification-160206090009.pdf
imageclassification-160206090009.pdfimageclassification-160206090009.pdf
imageclassification-160206090009.pdf
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
Neural networks
Neural networksNeural networks
Neural networks
 
[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare Events[PR12] PR-036 Learning to Remember Rare Events
[PR12] PR-036 Learning to Remember Rare Events
 
Machine Learning Live
Machine Learning LiveMachine Learning Live
Machine Learning Live
 
Lecture4 - Machine Learning
Lecture4 - Machine LearningLecture4 - Machine Learning
Lecture4 - Machine Learning
 
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
Piotr Mirowski - Review Autoencoders (Deep Learning) - CIUUK14
 
Variational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math BehindVariational Auto Encoder and the Math Behind
Variational Auto Encoder and the Math Behind
 
Deep learning from a novice perspective
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
 
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
AN ANN APPROACH FOR NETWORK INTRUSION DETECTION USING ENTROPY BASED FEATURE S...
 
Layering Based Network Intrusion Detection System to Enhance Network Attacks ...
Layering Based Network Intrusion Detection System to Enhance Network Attacks ...Layering Based Network Intrusion Detection System to Enhance Network Attacks ...
Layering Based Network Intrusion Detection System to Enhance Network Attacks ...
 
. An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic .... An introduction to machine learning and probabilistic ...
. An introduction to machine learning and probabilistic ...
 
Citython presentation
Citython presentationCitython presentation
Citython presentation
 

Mehr von Kyuri Kim

GPT-Series.pdf
GPT-Series.pdfGPT-Series.pdf
GPT-Series.pdfKyuri Kim
 
BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...
BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...
BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...Kyuri Kim
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networksKyuri Kim
 
Future semantic segmentation with convolutional LSTM
Future semantic segmentation with convolutional LSTMFuture semantic segmentation with convolutional LSTM
Future semantic segmentation with convolutional LSTMKyuri Kim
 
Exploring uncertainty measures in deep networks for sclerosis
Exploring uncertainty measures in deep networks for sclerosisExploring uncertainty measures in deep networks for sclerosis
Exploring uncertainty measures in deep networks for sclerosisKyuri Kim
 
Convolutional neural network based metal artifact reduction in x ray computed...
Convolutional neural network based metal artifact reduction in x ray computed...Convolutional neural network based metal artifact reduction in x ray computed...
Convolutional neural network based metal artifact reduction in x ray computed...Kyuri Kim
 
Automated bone metastasis detection
Automated bone metastasis detection Automated bone metastasis detection
Automated bone metastasis detection Kyuri Kim
 

Mehr von Kyuri Kim (7)

GPT-Series.pdf
GPT-Series.pdfGPT-Series.pdf
GPT-Series.pdf
 
BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...
BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...
BERT- Pre-training of Deep Bidirectional Transformers for Language Understand...
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
Future semantic segmentation with convolutional LSTM
Future semantic segmentation with convolutional LSTMFuture semantic segmentation with convolutional LSTM
Future semantic segmentation with convolutional LSTM
 
Exploring uncertainty measures in deep networks for sclerosis
Exploring uncertainty measures in deep networks for sclerosisExploring uncertainty measures in deep networks for sclerosis
Exploring uncertainty measures in deep networks for sclerosis
 
Convolutional neural network based metal artifact reduction in x ray computed...
Convolutional neural network based metal artifact reduction in x ray computed...Convolutional neural network based metal artifact reduction in x ray computed...
Convolutional neural network based metal artifact reduction in x ray computed...
 
Automated bone metastasis detection
Automated bone metastasis detection Automated bone metastasis detection
Automated bone metastasis detection
 

Kürzlich hochgeladen

(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxupamatechverse
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
Glass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesGlass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesPrabhanshu Chaturvedi
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxpranjaldaimarysona
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...ranjana rawat
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escortsranjana rawat
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSSIVASHANKAR N
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordAsst.prof M.Gokilavani
 
UNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and workingUNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and workingrknatarajan
 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxupamatechverse
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Call Girls in Nagpur High Profile
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Christo Ananth
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSISrknatarajan
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxupamatechverse
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college projectTonystark477637
 

Kürzlich hochgeladen (20)

(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(PRIYA) Rajgurunagar Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
Glass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesGlass Ceramics: Processing and Properties
Glass Ceramics: Processing and Properties
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptx
 
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
(INDIRA) Call Girl Aurangabad Call Now 8617697112 Aurangabad Escorts 24x7
 
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
The Most Attractive Pune Call Girls Budhwar Peth 8250192130 Will You Miss Thi...
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
 
UNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and workingUNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and working
 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
 
Introduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptxIntroduction to IEEE STANDARDS and its different types.pptx
Introduction to IEEE STANDARDS and its different types.pptx
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college project
 

Auto-encoding variational bayes

  • 1. Auto-Encoding Variational Bayes Diederik P. Kingma, Max Welling Machine Learning Group Universiteit van Amsterdam ICLR 2014 conference submission, Cited by 4655 May 23, 2019 SMC AI Research Center Kyuri Kim
  • 2. Introduction 1.1 Supervised learning vs. Unsupervised learning Supervised learning Ex. Classification Regression Object Detection Semantic Segmentation Image captioning : Data: (x, y) x is data, y is label Learn a function to map x → y Unsupervised learning Ex. Clustering Dimensionality Reduction Density estimation Feature Learning : Data: (x) Just data, no label Learn something underlying hidden structure of the data 1-d Density estimation 2-d Density estimation Ex. Image Detection Ex. 2
  • 3. Introduction 1.2 Auto Encoder (Feature Learning) 1. Unsupervised Learning 2. ML density estimation 3. Manifold Learning 4. Generative model learning In Auto Encoder Training: In Trained Auto Encoder : Encoding Decoding Latent Variable 𝝌 𝒙 L (𝝌, 𝒚) Reconstruction Error Decoder는 최소한의 학습 데이터는 생성해 낼 수 있고, Encoder는 최소한의 학습 데이터는 latent vector로 표현할 수 있다. Minimize 𝒁 3 𝑥)
  • 4. Introduction 1.3 Generative Model Given training data, generate new samples from same distribution Ex. Variational Auto encoders (VAE), Generative Adversarial Network(GAN) Generated samples ~ 𝑝 𝑚𝑜𝑑𝑒𝑙(𝑥)Training data ~ 𝑝 𝑑𝑎𝑡𝑎(𝑥) Want to learn 𝒑 𝒎𝒐𝒅𝒆𝒍 𝒙 similar to ~ 𝒑 𝒅𝒂𝒕𝒂(𝒙) Probability density function 4
  • 5. Introduction 1.4 Generative Model Network Generative model taxonomy Ian Goodfellow, "NIPS 2016 Tutorial: Generative Adversarial Networks" 5
  • 6. Experiments 2.1 Variational Auto-Encoder Target Data 𝝌 Latent Variable 𝑧 P(𝑥|𝑧)P(𝑧) Sample from true prior Sample from true conditional Decoder Network How to Train the Model? 6 Maximum likelihood estimation
  • 7. Experiments 2.2 Variation Inference Variation InferenceTarget Data Generator 𝒈 𝜽(.) 𝝌 Latent Variable 𝑝 (𝑧|𝑥) ≈ 𝑞 𝜙(𝑧|𝑥)~𝑧 sampling 𝑧 from 𝑝(𝑧|𝑥) Z를 정규분포에서 Sampling하는 것 보다 x와 유의미하게 Sample이 나올 수 있는 확률 분포 𝑝(𝑧|𝑥)로부터 Sampling. 그러나 𝑝(𝑧|𝑥)가 무엇인지 알지 못하므로, 우리가 알고 있는 확률분포 중 하나를 택하여 𝑞 𝜙(𝑧|𝑥) 그것의 parameter 값을 조정, 𝑝(𝑧|𝑥)과 유사하게 만든다. 7 𝑧
  • 8. Experiments 2.3 Variational Auto-Encoder (1) Definition of VAE Variational Inference를 Auto Encoder의 구조를 통해 구현한 Generate Model. (2) Structure of VAE When z is deterministic value On the respects of probability Where z is in a distribution X가 주어졌을 때 z의 확률 Variational Inference 𝑧 𝒈 𝜽(.)𝒒∅(.) 𝝌𝝌 𝑝(𝑧|𝑥) ≈ 𝑝(𝑧) 8
  • 9. Experiments 2.4 ELBO(Evidence Lower Bound) ELBO(Evidence Lower Bound) Variational Inference Jensen’s Inequality 9
  • 10. Experiments 2.4 ELBO(Evidence Lower Bound) ELBO(Evidence Lower Bound) KL term 두 확률분포 간의 거리 ≥ 0 10
  • 11. Experiments 2.4 ELBO(Evidence Lower Bound) KL term ① ③ ② 11
  • 12. Experiments 2.4 ELBO(Evidence Lower Bound) 𝒈 𝜽(𝒙|𝒛)𝒒∅(𝒛|𝒙) Encoder Inference Network Decoder Generation Network sampling Reconstruction error Regularization 12
  • 16. Appendix - Auto Encoder “어떤 방식으로 pre train하였는가?” 16