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
170
[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
200
[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
490
Introduction of PAC-Bayes and its Application for Contrastive Unsupervised Representation Learning
nzw0301
2
820
NLP Tutorial; word representation learning
nzw0301
0
220
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
250830 IaCの選定~AWS SAMのLambdaをECSに乗り換えたときの備忘録~
east_takumi
0
380
GitHubとGitLabとAWS CodePipelineでCI/CDを組み比べてみた
satoshi256kbyte
4
150
ぬるぬる動かせ! Riveでアニメーション実装🐾
kno3a87
1
130
Design Foundational Data Engineering Observability
sucitw
3
180
Swift Updates - Learn Languages 2025
koher
2
460
アプリの "かわいい" を支えるアニメーションツールRiveについて
uetyo
0
210
フロントエンドのmonorepo化と責務分離のリアーキテクト
kajitack
2
160
go test -json そして testing.T.Attr / Kyoto.go #63
utgwkk
3
270
オープンセミナー2025@広島「君はどこで動かすか?」アンケート結果
satoshi256kbyte
0
260
AIと私たちの学習の変化を考える - Claude Codeの学習モードを例に
azukiazusa1
2
1.2k
奥深くて厄介な「改行」と仲良くなる20分
oguemon
1
460
Ruby Parser progress report 2025
yui_knk
1
300
Featured
See All Featured
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
Statistics for Hackers
jakevdp
799
220k
Imperfection Machines: The Place of Print at Facebook
scottboms
268
13k
Documentation Writing (for coders)
carmenintech
74
5k
Fireside Chat
paigeccino
39
3.6k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
46
7.6k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
51
5.6k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
30
9.6k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3k
jQuery: Nuts, Bolts and Bling
dougneiner
64
7.9k
The Language of Interfaces
destraynor
161
25k
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