Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Variational Auto Encoderでの Disentangled表現
Search
Kosuke Miyoshi
November 03, 2016
Research
640
0
Share
Variational Auto Encoderでの Disentangled表現
※ Speaker Deck内ではURLリンクがクリックできないので、クリックしたい場合はpdfをダウンロードしてください
Kosuke Miyoshi
November 03, 2016
More Decks by Kosuke Miyoshi
See All by Kosuke Miyoshi
Representation Learning with Contrastive Predictive Coding
miyosuda
1
230
Sutton "Reinforcement Learning" 2nd Edition Ch13: Policy Gradient Methods
miyosuda
0
210
Sutton "Reinforcement Learning" 2nd Edition Ch7: n-step Bootstrapping
miyosuda
0
110
Sutton "Reinforcement Learning" 2nd Edition Ch6: TD-learning
miyosuda
0
110
SCAN
miyosuda
0
870
TensorFlow & DeepMind Lab & UNREAL
miyosuda
1
2.6k
Other Decks in Research
See All in Research
AIスーパーコンピュータにおけるLLM学習処理性能の計測と可観測性 / AI Supercomputer LLM Benchmarking and Observability
yuukit
1
830
ブレグマン距離最小化に基づくリース表現量推定:バイアス除去学習の統一理論
masakat0
0
240
[BlackHatAsia2026] Hidden Telemetry: Uncovering TraceLogging ETW Providers You're Not Using (Yet)
asuna_jp
0
300
「行ける・行けない表」による地域公共交通の性能評価
bansousha
0
140
通時的な類似度行列に基づく単語の意味変化の分析
rudorudo11
0
260
競合や要望に流されない─B2B SaaSでミニマム要件を決めるリアルな取り組み / Don't be swayed by competitors or requests - A real effort to determine minimum requirements for B2B SaaS
kaminashi
0
1.4k
「なんとなく」の顧客理解から脱却する ──顧客の解像度を武器にするインサイトマネジメント
tajima_kaho
10
7.4k
LINEヤフー データサイエンス Meetup「三井物産コモディティ予測チャレンジ」の舞台裏-AlpacaTechパート
gamella
0
420
第66回コンピュータビジョン勉強会@関東 Epona: Autoregressive Diffusion World Model for Autonomous Driving
kentosasaki
0
570
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
320
"主観で終わらせない"定性データ活用 ― プロダクトディスカバリーを加速させるインサイトマネジメント / Utilizing qualitative data that "doesn't end with subjectivity" - Insight management that accelerates product discovery
kaminashi
16
24k
Collective Predictive Coding and World Models in LLMs: A System 0/1/2/3 Perspective on Hierarchical Physical AI (IEEE SII 2026 Plenary Talk)
tanichu
1
370
Featured
See All Featured
How to train your dragon (web standard)
notwaldorf
97
6.6k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
davidcarrasco
3
110
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.8k
Code Reviewing Like a Champion
maltzj
528
40k
The Illustrated Children's Guide to Kubernetes
chrisshort
51
52k
VelocityConf: Rendering Performance Case Studies
addyosmani
333
25k
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
Ten Tips & Tricks for a 🌱 transition
stuffmc
0
99
Dominate Local Search Results - an insider guide to GBP, reviews, and Local SEO
greggifford
PRO
0
150
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
1
530
Practical Orchestrator
shlominoach
191
11k
Transcript
7BSJBUJPOBM"VUP&ODPEFSͰͷ %JTFOUBOHMFEදݱ OBSSBUJWFOJHIUTגࣜձࣾࡾ߁༞ શΞʔΩςΫνϟୈճ4*(8#"Φϑձ
&BSMZ7JTVBM$PODFQU-FBSOJOHXJUI 6OTVQFSWJTFE%FFQ-FBSOJOH Irina Higgins, Loic Matthey, Xavier Glorot, Arka Pal,
Benigno Uria, Charles Blundell, Shakir Mohamed, Alexander Lerchner Google DeepMind, 2016 ͱΓ͋͛Δจ ˞όʔδϣϯʹΑͬͯύϥϝʔλ͕େ͖͘ҧ͍ͬͯΔɻ࠷৽ͷWΛར༻
%JTFOUBOHMFE SFQSFTFOUBUJPO w ҙຯۭؒͷදݱΛɺҐஔɺαΠζɺFUDʜͳͲͷߏ ཁૉͷύϥϝʔλʹ͔Εͨঢ়ଶͰ֫ಘ͍ͨ͠ w 7BSJBUJPOBM"VUP&ODPEFSͷજࡏมͰ͜ΕΒͷ දݱΛڭࢣͳ͠Ͱ֫ಘͰ͖ͳ͍͔ʁ
7BSJBUJPOBM"VUP&ODPEFS 9 [ 9` FODPEFS EFDPEFS αϯϓϦϯά
7BSJBUJPOBM"VUP&ODPEFS zͷࣄޙۙࣅq(z|x) (=Τϯίʔμͷग़ྗ ͱ N(0,I)ͱͷڑΛ࠷খԽ ෮ݩޡࠩΛ࠷খԽ
Ќͩͱzͷࣄޙۙࣅq(z|x)ΛΑΓ N(0,I)ʹ͚ۙͮΑ͏ͱ͢Δ ਖ਼ଇԽ߲ʹЌΛಋೖ Ќͷࢹ֮࿏ʹ͋ΔύϥϝʔλʁΛۙࣅ
w Y࠲ඪ Z࠲ඪͦΕͧΕύλʔϯ w TDBMFύλʔϯ w ճసύλʔϯ w ΦϒδΣΫτͷܗ ପԁɺϋʔτɺ࢛֯
ύλʔϯ Yͷը૾ݸΛજࡏมݸͷ7"&Ͱֶश [ FODPEFS EFDPEFS αϯϓϦϯά ͷμ,σ
Ќ Ќ
N(0, I)ʹٵ͍ࠐ·Εͯ͠·͍ͬͯΔ જࡏมݸͷ͏ͪͷͻͱͭͷЖ͚ͩΛม͑ͯΓΛݻఆ ֤જࡏม͕ύϥϝʔλ͝ͱʹ ͔Ε͍ͯΔ જࡏมͷࢄ જࡏมͷЖΛdͰ ಈ͔͢
%FFQ.JOEʹΑΔͦͷଞͷ࣮ݧ݁Ռ IUUQUJOZVSMDPNKHCZ[LF "UBSJ %໎࿏FUD…
7"&Ͱ%JTFOUBOHMF͞ΕΔʹ w ม͕࿈ଓͰຶʹαϯϓϦϯά͞Ε͍ͯΔ w ཁૉ͕౷ܭతʹಠཱ w ੑ͕ݮΒ͞Ε͍ͯΔ
w ີʹαϯϓϦϯά͞Ε͍ͯΕɺೋ͕ͭผͷΦϒδΣΫτͩͱೝࣝͰ͖Δ
ಈ͖͕࿈ଓͰີʹαϯϓϦϯά͞Ε͍ͯΕɺ ಉ͡ΦϒδΣΫτͩͱೝࣝͰ͖Δ ͜ΕΒೋͭͷύυϧಉ͡ΦϒδΣΫτͩΖ͏͔ʁ
࠶ݱݕূ ETIBQF
࠶ݱݕূ #SFBLPVU ΫϦοΫͰ࠶ੜ wϒϩοΫͷมԽ͕ͭͬͨજࡏมʹ·͕ͨͬͯऔΕ͍ͯΔ จͷ༷ͳύυϧͷಈ͖είΞͷมԽ·ͩऔΕ͍ͯͳ͍ wЌΛڧ͘͢Δͱͬͯ͘Δજࡏมݮͬͯ͘Δ͕ɺಉ࣌ʹϘέ ۩߹͕େ͖͘ͳͬͯύυϧ͕ফ͑ͯ͠·͏ [ [
[