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
入門AlphaGo
Search
na-o-ys
April 22, 2016
Technology
5
3.6k
入門AlphaGo
"Mastering the game of Go with deep neural networks and tree search" の概要
na-o-ys
April 22, 2016
Tweet
Share
More Decks by na-o-ys
See All by na-o-ys
IoTと監視
naoys
1
600
RubyとJIT
naoys
0
130
将棋盤を画像認識したかった
naoys
0
1.4k
Rust で乗り換え案内
naoys
0
590
疎行列と Jaccard 類似度の高速計算
naoys
1
460
有理数集合の濃度
naoys
2
95
YARVの最適化について調べた
naoys
0
100
転職会議サービスのAWS移行記録
naoys
0
29
Anonymous Recursion in C++
naoys
0
390
Other Decks in Technology
See All in Technology
家族アルバム みてねで直面してきた技術的負債 / MIXI KAG 2024
isaoshimizu
17
7.7k
Autify Company Deck
autifyhq
1
30k
HoneycombとOpenTelemetryでオブザーバビリティに入門してみる
sumiren
2
160
現実世界の事象から学ぶSOLID原則
h0r15h0
24
10k
Oracle Database で機械学習を始めよう! Oracle Machine Learning
oracle4engineer
PRO
1
140
「XX試験の環境作ってよ」と言われた時によく使うAWSのソリューションについて
bun913
0
120
LLM + RAG を使った SORACOM Support Bot の裏側の歴史
soracom
PRO
1
640
Kubeflow Pipelines v2 で変わる機械学習パイプライン開発
asei
4
340
検証からプロダクトへ: シームレスなLLM開発の ためのしくみ作り
nunukim
1
200
8週連続ウェビナー_イチから学ぶFivetran
cmsuzu
0
170
AMLD 2024 - Build Your Own GPT
donlelef
1
260
Getting started with controlling LEGO using Swift
hcrane
0
130
Featured
See All Featured
Become a Pro
speakerdeck
PRO
8
4.4k
ParisWeb 2013: Learning to Love: Crash Course in Emotional UX Design
dotmariusz
101
6.6k
Six Lessons from altMBA
skipperchong
19
2.9k
Typedesign – Prime Four
hannesfritz
36
2k
We Have a Design System, Now What?
morganepeng
42
6.7k
StorybookのUI Testing Handbookを読んだ
zakiyama
10
4.5k
Raft: Consensus for Rubyists
vanstee
130
6.2k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
501
140k
Navigating Team Friction
lara
177
13k
Debugging Ruby Performance
tmm1
68
11k
VelocityConf: Rendering Performance Case Studies
addyosmani
319
23k
Bootstrapping a Software Product
garrettdimon
PRO
302
110k
Transcript
ೖAlphaGo 0x64ޠ ୈ07 “AI” @na_o_ys
͝ҙ • จʹॻ͔Ε͍ͯͳ͍ಠࣗௐࠪਪଌؚ͕· Ε·͢ • Ұߟͩͱࢥͬͯݟ͍ͯͩ͘͞
AlphaGoͱ • ॳΊͯϓϩع࢜ΛഁͬͨғޟAI
ୈҰ෦: AlphaGoʹࢸΔ·Ͱ
શใήʔϜ • ΦηϩɺνΣεɺকعɺғޟɺetc • ϥϯμϜੑ͕ແ͘ɺ࠷ળख͕ଘࡏ͢Δ • (ݪཧతʹ) ઌखඞউɾޙखඞউɾҾ͖͚
ήʔϜ • શ୳ࡧͰ࠷ળख͕ٻ·Δ • ܭࢉྔతʹෆՄೳ … ݱہ໘ 1खޙ 2खޙ
ධՁؔ • ൫໘Λ༩͑ΔͱείΞ (༧উͳͲ) Λฦؔ͢ • কعνΣεͳΒɺۨͷଛಘޮ͖ͷΛݩʹܭࢉ • ήʔϜͷ୳ࡧൣғ(ਂ͞)ΛݶఆͰ͖Δ ݱہ໘
1खޙ 2खޙ ධՁˠ 0.1 0.8 0.3 0.4
ධՁؔͷ༗ޮੑ • ύϥϝʔλͷબఆɾઃఆ͕ΩϞ • ख࡞ۀ: νΣεͰਓؒΛ͑ͨ • ػցֶश: কعͰਓؒΛ͑ͨ •
ғޟෳࡶੑͷͨΊʹ·ͱͳධՁؔΛ࡞Εͳ͔ͬ ͨ
ݪ࢝ϞϯςΧϧϩ๏ • ϥϯμϜʹऴہ·Ͱଧͭ (ϩʔϧΞτ) Λ܁Γฦͯ͠ɺউΛܭ ࢉ͢Δํ๏ ϩʔϧΞτΛ܁Γฦͯ͠ উΛܭࢉ উ 7/10
উ 3/10
ϞϯςΧϧϩ୳ࡧ (MCTS) • ݪ࢝ϞϯςΧϧϩ๏ΛධՁؔతʹ͏ • n खઌͰϩʔϧΞτ • ༿ͷউΛܭࢉ ※͞Βʹ༿ͷউʹԠͯ͡ಈతʹࢬמΓɾల։͠ɺ୳ࡧਫ਼Λ্͛Δ
ϙϦγʔؔ • f (ہ໘, ࣍ͷҰख) • ࣍ͷҰखͷࣗવ͞Λ͋ΒΘ֬͢ີؔ • عේσʔλ͔Βͷֶश͕༰қ •
ϩʔϧΞτ࣌ʹ͑Δ • ϥϯμϜʹଧͭͷͰͳ͘ɺ·ͱͳखΛଧͨͤΔ • ͨͩ͠ߴʹಈ࡞͢Δඞཁ͕͋Δ
MCTSͷڧ͞ • ϙϦγʔؔͷͳͲͰΞϚνϡΞߴஈʹඖఢ͢Δڧ͞· Ͱਐา • ϓϩʹٴͳ͍ • େہ؍ʹ༏ΕΔ • ʮڱ͘ਂ͍ಡΈʯ͕ऑ͍
• खΛ͘ಡΉͨΊ
AlphaGo͕ͬͨ͜ͱ • جຊMCTS • ༷ʑͳ • CNN(ΈࠐΈχϡʔϥϧωοτϫʔΫ) • ڧԽֶश •
ධՁؔ • ฒྻࢄΞϧΰϦζϜ • MCTS ʹͦΕΒΛΈࠐΜͩ
ୈೋ෦: AlphaGo
2ͭͷϙϦγʔؔͱ 1ͭͷධՁؔ ϩʔϧΞτϙϦγʔ ϩʔϧΞτʹ͏ ߴɾਫ਼ 4-ϙϦγʔ ୳ࡧॱংΛܾΊΔ ɾߴਫ਼ ධՁؔ ༿ͷධՁ(উ)Λܭࢉ
ϩʔϧΞτʹΑΔউͱ͠߹ΘͤΔ
ϩʔϧΞτϙϦγʔ • ϩʔϧΞτ(ϥϯμϜϓϨΠ)ʹ͏ϙϦγʔؔ • ߴੑɹʼɹਫ਼ • ਓؒͷعේ800ສہ໘͔Βֶश • ઢܗιϑτϚοΫεؔ •
2ϚΠΫϩඵ (ߴ) • عේͱͷࢦ͠खҰக: 24.2%
SLϙϦγʔ • ͷ୳ࡧॱংΛܾΊΔϙϦγʔؔ • ਫ਼ɹʼɹߴੑ • ਓؒͷعේ3000ສہ໘͔Βֶश • 13CNN(ΈࠐΈχϡʔϥϧωοτϫʔΫ) •
ը૾ೝࣝͰΑ͘ΘΕΔ • : 3ϛϦඵ • عේͱͷࢦ͠खҰக: 57%
ධՁؔ • 14CNN • SLϙϦγʔΛڧԽֶशͨ͠ͷ (RLϙϦγʔ) Λݩʹɺճؼͯ͠࡞Δ 4-ϙϦγʔ 3-ϙϦγʔ ධՁؔ
1. ڧԽֶश 2. ϥϯμϜعේੜ (3000ສہ໘) 3. ճؼ
ධՁؔͷଊ͑ํ • ϩʔϧΞτʹΑΔউܭࢉΛิ͏ͷ • ୯ମͰͦ͜·Ͱڧ͘ͳ͍ • ධՁؔͷಛ (ߟ) • ʮڱ͘ਂ͍ಡΈʯʹڧ͍
• ʮRLϙϦγʔ(ڧԽֶश݁Ռ)Λऴہ·ͰଧͨͤͨࡍͷউʯͱՁ • େہ؍͕ແ͍ • Ұຊಓ͔͠ಡ·ͳ͍ .$54ͷಛੑ େہ؍ʹ༏Εͯʮਂ͍ಡΈʯ͕ऑ͍ ͱ ͏·͘ิ͍͍͋ͬͯΔ
ڧ͞ (2015/10࣌)
ڧ͞ (2016/3 ࣌) R3500+ ͷΠɾηυϧʹউ
ࢀߟ • Mastering the game of Go with deep neural
networks and tree search (http://www.nature.com/nature/journal/v529/n7587/full/ nature16961.html) • Google AlphaGoͷΈΛཧղ͢Δ | IT Leaders (http://it.impressbm.co.jp/articles/-/13474)
ऴΘΓ