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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Kosuke Miyoshi
November 03, 2016
Research
0
640
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
Tweet
Share
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
100
Sutton "Reinforcement Learning" 2nd Edition Ch6: TD-learning
miyosuda
0
110
SCAN
miyosuda
0
850
TensorFlow & DeepMind Lab & UNREAL
miyosuda
1
2.6k
Other Decks in Research
See All in Research
Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
satai
3
650
離散凸解析に基づく予測付き離散最適化手法 (IBIS '25)
taihei_oki
1
730
衛星×エッジAI勉強会 衛星上におけるAI処理制約とそ取組について
satai
4
340
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
400
SREはサイバネティクスの夢をみるか? / Do SREs Dream of Cybernetics?
yuukit
3
440
2026-01-30-MandSL-textbook-jp-cos-lod
yegusa
1
710
【SIGGRAPH Asia 2025】Lo-Fi Photograph with Lo-Fi Communication
toremolo72
0
130
LiDARセキュリティ最前線(2025年)
kentaroy47
0
290
[チュートリアル] 電波マップ構築入門 :研究動向と課題設定の勘所
k_sato
0
340
「車1割削減、渋滞半減、公共交通2倍」を 熊本から岡山へ@RACDA設立30周年記念都市交通フォーラム2026
trafficbrain
1
780
YOLO26_ Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
satai
3
140
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
1.2k
Featured
See All Featured
How to Ace a Technical Interview
jacobian
281
24k
Documentation Writing (for coders)
carmenintech
77
5.3k
Collaborative Software Design: How to facilitate domain modelling decisions
baasie
0
160
Context Engineering - Making Every Token Count
addyosmani
9
760
Are puppies a ranking factor?
jonoalderson
1
3.1k
Making Projects Easy
brettharned
120
6.6k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
64
52k
Navigating Team Friction
lara
192
16k
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
0
100
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4k
Un-Boring Meetings
codingconduct
0
230
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
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·͏ [ [
[