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
城ヶ崎美嘉で学ぶRNNLM
Search
Kento Nozawa
June 05, 2016
Programming
2
3k
城ヶ崎美嘉で学ぶRNNLM
オタク機械学習勉強会#0 のLT
Kento Nozawa
June 05, 2016
Tweet
Share
More Decks by Kento Nozawa
See All by Kento Nozawa
Analysis on Negative Sample Size in Contrastive Unsupervised Representation Learning
nzw0301
0
160
[IJCAI-ECAI 2022] Evaluation Methods for Representation Learning: A Survey
nzw0301
0
610
[NeurIPS Japan meetup 2021 talk] Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
nzw0301
0
190
[IBIS2021] 対照的自己教師付き表現学習おける負例数の解析
nzw0301
0
180
Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
nzw0301
0
480
Introduction of PAC-Bayes and its Application for Contrastive Unsupervised Representation Learning
nzw0301
2
810
NLP Tutorial; word representation learning
nzw0301
0
210
Analyzing Centralities of Embedded Nodes
nzw0301
0
170
Paper Reading: Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics
nzw0301
2
1.2k
Other Decks in Programming
See All in Programming
今ならAmazon ECSのサービス間通信をどう選ぶか / Selection of ECS Interservice Communication 2025
tkikuc
21
3.9k
『自分のデータだけ見せたい!』を叶える──Laravel × Casbin で複雑権限をスッキリ解きほぐす 25 分
akitotsukahara
2
620
なぜ「共通化」を考え、失敗を繰り返すのか
rinchoku
1
640
Modern Angular with Signals and Signal Store:New Rules for Your Architecture @enterJS Advanced Angular Day 2025
manfredsteyer
PRO
0
200
プロダクト志向ってなんなんだろうね
righttouch
PRO
0
180
XP, Testing and ninja testing
m_seki
3
240
PipeCDのプラグイン化で目指すところ
warashi
1
260
PostgreSQLのRow Level SecurityをPHPのORMで扱う Eloquent vs Doctrine #phpcon #track2
77web
2
510
ペアプロ × 生成AI 現場での実践と課題について / generative-ai-in-pair-programming
codmoninc
1
15k
Rubyでやりたい駆動開発 / Ruby driven development
chobishiba
1
650
GraphRAGの仕組みまるわかり
tosuri13
8
530
Porting a visionOS App to Android XR
akkeylab
0
380
Featured
See All Featured
Fireside Chat
paigeccino
37
3.5k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
Measuring & Analyzing Core Web Vitals
bluesmoon
7
500
Embracing the Ebb and Flow
colly
86
4.7k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
How GitHub (no longer) Works
holman
314
140k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
107
19k
The Cost Of JavaScript in 2023
addyosmani
51
8.5k
The Straight Up "How To Draw Better" Workshop
denniskardys
234
140k
Automating Front-end Workflow
addyosmani
1370
200k
StorybookのUI Testing Handbookを読んだ
zakiyama
30
5.9k
Transcript
ϲ࡚ඒՅ Λը૾ݕࡧ͓ͯͪ͠Լ͍͞
ϲ࡚ඒՅͰֶͿ RNNLM 2016/6/5 ΦλΫػցֶशษڧձ #0 @nzw0301
Ϟνϕʔγϣϯ ϲ࡚ඒՅͷηϦϑੜ
Recurrent Neural Network Language Model • ηϦϑੜ: લ·Ͱͷ୯ޠ͔Β࣍ͷ1୯ޠΛ༧ଌ͠ଓ͚Δ • ྫɿΊΔΊΔʜᣦՅʹϝʔϧૹ৴ͬ˒
• ୯ޠׂ: <BOS> ΊΔΊΔʜᣦՅʹϝʔϧૹ৴ͬ˒&04 • ֶश: Q ΊΔΊΔc#04 ͱ͔ Q ᣦՅc<BOS>, ΊΔΊΔ ʜ
RNNLMͷߏ ޠኮV࣍ݩͷϕΫτϧ softmax ؔ 1ͭલͷதؒͷϕΫτϧ RNNͷ༝ԑ h࣍ݩͷதؒ
p(ΊΔΊΔ|<BOS>) ͷܭࢉྫɿೖྗ w #04ͷPOFPG,දݱΛೖྗ w ࣍ݩͰີͳϕΫτϧʹม <BOS> ΊΔΊΔ 0 B
B B B B @ 0 1 0 . . . 0 1 C C C C C A
p(ΊΔΊΔ|<BOS>) ͷܭࢉྫɿதؒ • ີͳϕΫτϧΛதؒʹ͢ • ଟύʔηϓτϩϯͱಉ͡ <BOS> ΊΔΊΔ
p(ΊΔΊΔ|<BOS>) ͷܭࢉྫɿग़ྗ • ग़ྗʹதؒͷϕΫτϧΛ͢ • ݱࡏͷதؒͷΛอ࣋ <BOS> ΊΔΊΔ
p(ΊΔΊΔ|<BOS>) ͷܭࢉྫɿॏΈߋ৽ • SoftmaxؔͰ֬Λܭࢉ • Backpropagation Ͱ ΊΔΊΔ ͷ͕֬େ͖͘ͳΔΑ͏ʹߋ৽ <BOS>
ΊΔΊΔ
p(ʜc#04 ΊΔΊΔ) ͷܭࢉྫɿೖྗ ૄΊΔΊΔϕΫτϧΛೖྗ͠ɼີͳΊΔΊΔϕΫτϧʹม p(ΊΔΊΔ|<BOS>)Ͱܭࢉͨ͠தؒͷϕΫτϧ ʜ ΊΔΊΔ 0 B B
B B B B B B B B @ 0 . . . 0 1 0 . . . 0 1 C C C C C C C C C C A
p(ʜc#04 ΊΔΊΔ) ͷܭࢉྫɿதؒ ີͳΊΔΊΔϕΫτϧͱલʹܭࢉͨ͠தؒͷϕΫτϧΛதؒ p(ΊΔΊΔ|<BOS>)Ͱܭࢉͨ͠தؒͷϕΫτϧ ʜ ΊΔΊΔ
p(ʜc#04 ΊΔΊΔ) ͷܭࢉྫɿग़ྗ • ग़ྗʹதؒͷϕΫτϧΛͯ͠ɼݱࡏͷதؒͷϕΫτϧΛอ࣋ p(ʜ|<BOS>, ΊΔΊΔ)Ͱܭࢉͨ͠தؒͷϕΫτϧ ʜ ΊΔΊΔ
p(ʜc#04 ΊΔΊΔ) ͷܭࢉྫɿॏΈߋ৽ • SoftmaxؔͰ֬Λܭࢉ • Backpropagation Ͱ ʜ ͷ͕֬େ͖͘ͳΔΑ͏ʹߋ৽
ʜ ΊΔΊΔ
࣮ݧ
࣮ݧ֓ཁ • SCRNΛ༻ • LSTM GRU ΛΘͳ͍ • Keras
Ͱ࣮ • લॲཧ • ܗଶૉղੳͤͣʹจࣈ୯ҐͰֶश • /。|★|?|!|♪/ ͰηϦϑΛׂ • 900ηϦϑ (Վࢺ) Λ༻ • ϞόϚε • σϨες • TOKIMEKIΤεΧϨʔτ
݁Ռ
10epochޙɿϓϩσϡʔαʔͷҰ෦͕ͱΕͯΔ ϓϩσϩσϡʔͯͳͪʙʹෲΞλ γ΄ϡʔαʔΒతͳʔɺͨ͜ͳ
40epochޙɿΪϟϧޠʁ ϓϩσϡʔαʔʹ͍ͪΌΜɺ ݟ͘ͳ͍ʔ͘ͱԿߴͩ͠ʔͬ̇
80epochޙɿݺΕͨؾ͕ͨ͠ ϓϩσϡʔαʔ!
“<BOS> ϓ” ͔Β࠷ਪఆɿϧʔϓ ϓϩσϡʔαʔɺΞλγͷ͜ͱ͔Βɺ ϓϩσϡʔαʔɺΞλγͷ͜ͱ
ϥϯμϜʹηϦϑੜ
ॴײ • ηϦϑΛͲ͜ͰΔ͖͔ • ྫɿ͝Μʹ͢Δ?͓෩࿊ʹ͢Δ?…͜ΕͪΐͬͱϕλͬΆ͍ͳ͊ • ? Ͱ۠Δ͖͔൱͔ • …લޙͲͬͪͰ۠Δ͔൱͔ʁͦΕͱͳ͘͢ʁ
• ήʔϜը໘ͷͨΊ͔1ηϦϑܥྻ͕΄΅Ұఆʢֶͼʣ
ࢀߟจݙͳͲ • http://keras.io/ • DLͷϥΠϒϥϦ • ָ͍͢͝ʹॻ͚Δ • Mikolov at.el.
Recurrent neural network based language model. 2010. • RNNͷը૾͜ͷจͷͷΛ༻ • Mikolov at.el Learning Longer Memory in Recurrent Neural Networks. 2014. • ࠓճ༻ͨ͠Ϟσϧ