SlideShare une entreprise Scribd logo
1  sur  41
Télécharger pour lire hors ligne
Wasserstein GAN
2017-07-12 NN #3 @ TFUG
Yuta Kashino ( )
BakFoo, Inc. CEO
Astro Physics /Observational Cosmology
Zope / Python
Realtime Data Platform for Enterprise / Prototyping
Yuta Kashino ( )
arXiv
stat.ML, stat.TH, cs.CV, cs.CL, cs.LG
math-ph, astro-ph
- PyCon2016
- PyCon2017 Edward
- 2017 8 TFUG
@yutakashino
https://www.slideshare.net/yutakashino/pyconjp2016
Wasserstein GAN
…
- WGAN: GAN
-
- DCGAN
-
-
Generative Adversarial
Networks
GAN 1
- Generative Adversarial Networks
- Ian Goodfelow
- Bengio , Theano/Pyleran2
- Google Brain
- 2016 NIPIS Tutorial
- : The GAN Zoo
https://goo.gl/uC8xn2
https://github.com/hindupuravinash/the-gan-zoo
GAN 2
- GAN …
- Meow Generator
- HDCGAN, WGAN, LSGAN…
https://ajolicoeur.wordpress.com/cats/
https://github.com/hindupuravinash/the-gan-zoo
Vanila GAN
- Generator Discriminator min/max
- G D
- MLP
https://goo.gl/vHUpqG https://goo.gl/7u4zS6
DCGAN
-
- CNN
- G /D
- Pool/ Full Batch Norm, Leaky ReLU
Unsupervised Representation Learning with
Deep Convolutional Generative Adversarial Networks
https://arxiv.org/abs/1511.06434
https://goo.gl/8EmZgT
GAN
- G/D JS
-
-
-
-
-
Wasserstein GAN
WGAN 1
- / /
- /
-
-
-
-
- (
WGAN 2
-
- Read-through: Wasserstein GAN
- Wasserstein GAN and the Kantorovich-Rubinstein
Duality
-
https://goo.gl/7ywVwc
https://goo.gl/40eCbR
WGAN
GAN Descriminator/Critic W
1. W
( 1, 2)
2. W
( 3)
3. W
4.
WGAN
1. WGAN:
4
- Total Variation(TV)
- Kullback-Leibler (KL) divergence
- Jenson-Shannon (JS) divergence
- Earth Mover (EM) / Wasserstein
(Pr, Pg) = sup
A
|Pr(A) Pg(A)|
KL(PrkPg) =
Z
x
log
✓
Pr(x)
Pg(x)
◆
Pr(x) dx
JS(Pr, Pg) =
1
2
KL(PrkPm) +
1
2
KL(PgkPm)
M = Pr/2 + Pg/2M
W(Pr, Pg) = inf
2⇧(Pr,Pg)
E(x,y)⇠
⇥
kx yk
⇤
4
- W
- JS
- KL
- TV
KL(P0kP✓) = KL(P✓kP0) =
(
+1 if ✓ 6= 0 ,
0 if ✓ = 0 ,
(P0, P✓) =
(
1 if ✓ 6= 0 ,
0 if ✓ = 0 .
JS(P0, P✓) =
(
log 2 if ✓ 6= 0 ,
0 if ✓ = 0 ,
W(P0, P✓) = |✓|
U[0, 1]
https://goo.gl/40eCbR
3 1
- 1:
W
- 2:
W
W
- 1, 2
W GAN Loss
3 2
3: Kantorovich-Rubinstein
- W
- W
max
w2W
Ex⇠Pr
[fw(x)] Ex⇠P✓
[fw(x)]  sup
kfkLK
Ex⇠Pr
[f(x)] Ex⇠P✓
[f(x)]
= K · W(Pr, P✓)
r✓W(Pr, P✓) = r✓(Ex⇠Pr
[fw(x)] Ez⇠Z[fw(g✓(z))])
= Ez⇠Z[r✓fw(g✓(z))]
W/EM 1
-
-
W(Pr, Pg) = inf
2⇧(Pr,Pg)
E(x,y)⇠
⇥
kx yk
⇤
scypy.optimize.linprog
γ
https://goo.gl/7ywVwc
https://goo.gl/7ywVwc
W/EM 2
: Kantorovich-Rubinstein
-
W(Pr, Pg) = inf
2⇧(Pr,Pg)
E(x,y)⇠
⇥
kx yk
⇤
W(Pr, Pg) = sup
kfkL1
Ex⇠Pr
[f(x)] Ex⇠Pg
[f(x)]
3 2( )
3: Kantorovich-Rubinstein
- W
- W
max
w2W
Ex⇠Pr
[fw(x)] Ex⇠P✓
[fw(x)]  sup
kfkLK
Ex⇠Pr
[f(x)] Ex⇠P✓
[f(x)]
= K · W(Pr, P✓)
r✓W(Pr, P✓) = r✓(Ex⇠Pr
[fw(x)] Ez⇠Z[fw(g✓(z))])
= Ez⇠Z[r✓fw(g✓(z))]
2. WGAN:
r✓W(Pr, P✓) = r✓(Ex⇠Pr
[fw(x)] Ez⇠Z[fw(g✓(z))])
= Ez⇠Z[r✓fw(g✓(z))]
PyTorch
https://goo.gl/unktzn
3. WGAN:
- WGAN
- W
DCGAN
JS
WGAN
W
DCGAN
WGAN
DCGAN
BatchNorm OK
BatchNorm
WGAN
BatchNorm
DCGAN
OK
MLP
WGAN
MLP
DCGAN
-
-
- WGAN
- GAN G D
Improved Training of Wasserstein GANs
https://arxiv.org/abs/1704.00028
Do GANs actually learn the distribution? An empirical study
https://arxiv.org/abs/1706.08224
WGAN
GAN Descriminator/Critic W
1. W
( 1, 2)
2. W
( 3)
3. W
4.
Questions
kashino@bakfoo.com
@yutakashino
BakFoo, Inc.
NHK NMAPS: +
BakFoo, Inc.
PyConJP 2015
Python
BakFoo, Inc.
BakFoo, Inc.
: SNS +

Contenu connexe

Tendances

hadoop introduce
hadoop introducehadoop introduce
hadoop introduce
justlooks
 

Tendances (20)

Moving Biodiversity to the Cloud @TDWG09
Moving Biodiversity to the Cloud @TDWG09Moving Biodiversity to the Cloud @TDWG09
Moving Biodiversity to the Cloud @TDWG09
 
Clojure night
Clojure nightClojure night
Clojure night
 
What we got from the Predicting Red Hat Business Value competition
What we got from the Predicting Red Hat Business Value competitionWhat we got from the Predicting Red Hat Business Value competition
What we got from the Predicting Red Hat Business Value competition
 
Pig: Data Analysis Tool in Cloud
Pig: Data Analysis Tool in Cloud Pig: Data Analysis Tool in Cloud
Pig: Data Analysis Tool in Cloud
 
3. basic data structures(2)
3. basic data structures(2)3. basic data structures(2)
3. basic data structures(2)
 
Tree Top
Tree TopTree Top
Tree Top
 
hadoop introduce
hadoop introducehadoop introduce
hadoop introduce
 
Data visualization using case study
Data visualization using case studyData visualization using case study
Data visualization using case study
 
Latas bussines
Latas bussinesLatas bussines
Latas bussines
 
Coq for ML users
Coq for ML usersCoq for ML users
Coq for ML users
 
Nasamatic NewHaven.IO 2014 05-21
Nasamatic NewHaven.IO 2014 05-21Nasamatic NewHaven.IO 2014 05-21
Nasamatic NewHaven.IO 2014 05-21
 
module1
module1module1
module1
 
PyHEP 2019: Python Histogramming Packages
PyHEP 2019: Python Histogramming PackagesPyHEP 2019: Python Histogramming Packages
PyHEP 2019: Python Histogramming Packages
 
Loader and Tester Swarming Drones for Cellular Phone Network Loading and Fiel...
Loader and Tester Swarming Drones for Cellular Phone Network Loading and Fiel...Loader and Tester Swarming Drones for Cellular Phone Network Loading and Fiel...
Loader and Tester Swarming Drones for Cellular Phone Network Loading and Fiel...
 
CHEP 2019: Recent developments in histogram libraries
CHEP 2019: Recent developments in histogram librariesCHEP 2019: Recent developments in histogram libraries
CHEP 2019: Recent developments in histogram libraries
 
IoT Chess
IoT ChessIoT Chess
IoT Chess
 
Templating with your {{mustache}}js
Templating with your {{mustache}}jsTemplating with your {{mustache}}js
Templating with your {{mustache}}js
 
用 Bitbar Tool 寫 Script 自動擷取外幣
用 Bitbar Tool 寫 Script 自動擷取外幣用 Bitbar Tool 寫 Script 自動擷取外幣
用 Bitbar Tool 寫 Script 自動擷取外幣
 
PyHEP 2019: Python 3.8
PyHEP 2019: Python 3.8PyHEP 2019: Python 3.8
PyHEP 2019: Python 3.8
 
Всеволод Поляков (DevOps Team Lead в Grammarly)
Всеволод Поляков (DevOps Team Lead в Grammarly)Всеволод Поляков (DevOps Team Lead в Grammarly)
Всеволод Поляков (DevOps Team Lead в Grammarly)
 

Similaire à Wasserstein GAN Tfug2017 07-12

Similaire à Wasserstein GAN Tfug2017 07-12 (8)

ロマンティックな9つの数 #ロマ数ボーイズ
ロマンティックな9つの数 #ロマ数ボーイズロマンティックな9つの数 #ロマ数ボーイズ
ロマンティックな9つの数 #ロマ数ボーイズ
 
Towards formal verification of neural networks
Towards formal verification of neural networksTowards formal verification of neural networks
Towards formal verification of neural networks
 
uuum_3q
uuum_3quuum_3q
uuum_3q
 
統計的学習の基礎 4章 前半
統計的学習の基礎 4章 前半統計的学習の基礎 4章 前半
統計的学習の基礎 4章 前半
 
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
 
Evolution and AI
Evolution and AIEvolution and AI
Evolution and AI
 
「ベータ分布の謎に迫る」第6回 プログラマのための数学勉強会 LT資料
「ベータ分布の謎に迫る」第6回 プログラマのための数学勉強会 LT資料「ベータ分布の謎に迫る」第6回 プログラマのための数学勉強会 LT資料
「ベータ分布の謎に迫る」第6回 プログラマのための数学勉強会 LT資料
 
関西NIPS+読み会発表スライド
関西NIPS+読み会発表スライド関西NIPS+読み会発表スライド
関西NIPS+読み会発表スライド
 

Plus de Yuta Kashino

Gunosy go2015 06-02
Gunosy go2015 06-02Gunosy go2015 06-02
Gunosy go2015 06-02
Yuta Kashino
 

Plus de Yuta Kashino (20)

Python kansai2019
Python kansai2019Python kansai2019
Python kansai2019
 
Mlse20190208
Mlse20190208Mlse20190208
Mlse20190208
 
Pydata2017 11-29
Pydata2017 11-29Pydata2017 11-29
Pydata2017 11-29
 
PyConJP2016: 週末サイエンティストのススメ
PyConJP2016: 週末サイエンティストのススメPyConJP2016: 週末サイエンティストのススメ
PyConJP2016: 週末サイエンティストのススメ
 
機械学習ビジネス研究会 第01回
機械学習ビジネス研究会 第01回機械学習ビジネス研究会 第01回
機械学習ビジネス研究会 第01回
 
深層学習ライブラリの環境問題Chainer Meetup2016 07-02
深層学習ライブラリの環境問題Chainer Meetup2016 07-02深層学習ライブラリの環境問題Chainer Meetup2016 07-02
深層学習ライブラリの環境問題Chainer Meetup2016 07-02
 
Chainer meetup2016 03-19pub
Chainer meetup2016 03-19pubChainer meetup2016 03-19pub
Chainer meetup2016 03-19pub
 
"Automatic Variational Inference in Stan" NIPS2015_yomi2016-01-20
"Automatic Variational Inference in Stan" NIPS2015_yomi2016-01-20"Automatic Variational Inference in Stan" NIPS2015_yomi2016-01-20
"Automatic Variational Inference in Stan" NIPS2015_yomi2016-01-20
 
深層学習ライブラリのプログラミングモデル
深層学習ライブラリのプログラミングモデル深層学習ライブラリのプログラミングモデル
深層学習ライブラリのプログラミングモデル
 
TensorFlow White Paperを読む
TensorFlow White Paperを読むTensorFlow White Paperを読む
TensorFlow White Paperを読む
 
Deep learning Libs @twm
Deep learning Libs @twmDeep learning Libs @twm
Deep learning Libs @twm
 
日本のオープンデータプラットフォームをPythonでつくる
日本のオープンデータプラットフォームをPythonでつくる日本のオープンデータプラットフォームをPythonでつくる
日本のオープンデータプラットフォームをPythonでつくる
 
Gunosy2015 09-16ts
Gunosy2015 09-16tsGunosy2015 09-16ts
Gunosy2015 09-16ts
 
Gunosy2015-08-05
Gunosy2015-08-05Gunosy2015-08-05
Gunosy2015-08-05
 
Gunosy2015 07-07
Gunosy2015 07-07Gunosy2015 07-07
Gunosy2015 07-07
 
Gunosy2015-06-03
Gunosy2015-06-03Gunosy2015-06-03
Gunosy2015-06-03
 
PyDataTokyo201-05-22
PyDataTokyo201-05-22PyDataTokyo201-05-22
PyDataTokyo201-05-22
 
Gunosy go2015 06-02
Gunosy go2015 06-02Gunosy go2015 06-02
Gunosy go2015 06-02
 
FLAME: Probabilistic Model Combining Aspect Based Opinion Mining and Collabor...
FLAME: Probabilistic Model Combining Aspect Based Opinion Mining and Collabor...FLAME: Probabilistic Model Combining Aspect Based Opinion Mining and Collabor...
FLAME: Probabilistic Model Combining Aspect Based Opinion Mining and Collabor...
 
Opendata@tokyowebmining
Opendata@tokyowebminingOpendata@tokyowebmining
Opendata@tokyowebmining
 

Dernier

Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
WSO2
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 

Dernier (20)

Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu SubbuApidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
Apidays Singapore 2024 - Modernizing Securities Finance by Madhu Subbu
 
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
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Architecting Cloud Native Applications
Architecting Cloud Native ApplicationsArchitecting Cloud Native Applications
Architecting Cloud Native Applications
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
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
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
Apidays Singapore 2024 - Scalable LLM APIs for AI and Generative AI Applicati...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 

Wasserstein GAN Tfug2017 07-12