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
Deep Learning Book 10その2 / deep learning book 1...
Search
himkt
January 29, 2018
Research
2
200
Deep Learning Book 10その2 / deep learning book 10 vol2
himkt
January 29, 2018
Tweet
Share
More Decks by himkt
See All by himkt
Linformer: paper reading
himkt
0
540
RoBERTa: paper reading
himkt
1
350
NLP SoTA 勉強会 / ner_2019
himkt
2
1.4k
自然言語処理 @ クックパッド / nlp at cookpad
himkt
1
530
Interpretable Machine Learning 6.3 - Prototypes and Criticisms
himkt
2
170
ニューラル固有表現抽出 / Neural Named Entity Recognition
himkt
3
750
ニューラル固有表現抽出器を実装してみる / PyNER
himkt
6
2.1k
Spacyでお手軽NLP / NLP with spacy
himkt
0
1k
ふわふわ系列ラベリング / ner 2018
himkt
5
850
Other Decks in Research
See All in Research
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
0
190
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
220
論文読み会 SNLP2025 Learning Dynamics of LLM Finetuning. In: ICLR 2025
s_mizuki_nlp
0
260
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
910
論文紹介:Not All Tokens Are What You Need for Pretraining
kosuken
0
190
Vision and LanguageからのEmbodied AIとAI for Science
yushiku
PRO
1
550
AI エージェントを活用した研究再現性の自動定量評価 / scisci2025
upura
1
160
Remote sensing × Multi-modal meta survey
satai
4
430
大規模な2値整数計画問題に対する 効率的な重み付き局所探索法
mickey_kubo
1
380
心理言語学の視点から再考する言語モデルの学習過程
chemical_tree
2
610
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
410
情報技術の社会実装に向けた応用と課題:ニュースメディアの事例から / appmech-jsce 2025
upura
0
190
Featured
See All Featured
RailsConf 2023
tenderlove
30
1.2k
Build your cross-platform service in a week with App Engine
jlugia
232
18k
Writing Fast Ruby
sferik
629
62k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
7
890
Scaling GitHub
holman
463
140k
The Straight Up "How To Draw Better" Workshop
denniskardys
237
140k
The Language of Interfaces
destraynor
162
25k
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.4k
A Modern Web Designer's Workflow
chriscoyier
697
190k
Large-scale JavaScript Application Architecture
addyosmani
514
110k
The Art of Programming - Codeland 2020
erikaheidi
56
14k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
1.6k
Transcript
&DIP4UBUF/FUXPSLT&YQMJDJU.FNPSZ IJNLU!य़ΤϦΞ DEEP LEARNING BOOK 4FRVFODF.PEFMJOH3FDVSSFOUBOE3FDVSTJWF/FUT
&DIP4UBUF/FUXPSLT w 3//ʹֶ͓͍ͯश͕େมͳύϥϝʔλ w ӅΕӅΕ SFDVSSFOUXFJHIUT w ೖྗӅΕ JOQVUXFJHIUT
w &DIP4UBUF/FUXPSL w ӅΕӅΕॏΈΛݻఆ w ֶश͢Δͷʜ w ೖྗӅΕ JOQVUXFJHIUT w ӅΕग़ྗ PVUQVUXFJHIUT
&DIP4UBUF/FUXPSLT IUUQXXXTDIPMBSQFEJBPSHBSUJDMF&DIP@TUBUF@OFUXPSL
,FSOFMNBDIJOFͱͷྨࣅੑ w Χʔωϧ͕ͬͯΔ͜ͱͬͯʁ w ҙͷ͞ͷܥྻΛݻఆͷϕΫτϧࣸ͢ w ݻఆͷϕΫτϧΛ༻͍ͯྨث͕Λղ͘ w ͜ͷܗͷ߹ɼֶशͷج४ͷઃܭ͕༰қͰ͋Δ w
ग़ྗઢܗճؼͷ߹.4&ͰֶशͰ͖Δ w &4/TೖྗΛԿΒ͔ͷϕΫτϧʹࣸ͢ૢ࡞Λ͍ͯ͠Δ w தͷॏΈݻఆ͍ͯ͠Δ ͍͔ʹաڈͷใΛ๛ʹؚΉදݱ͕ಘΒΕΔ ॏΈΛઃఆ͢ΕΑ͍͔ʁ શવҙຯ͕Θ͔Βͣʜ 3//ΛಈతγεςϜͱΈͳ͢ γεςϜ͕҆ఆ͢ΔΑ͏ͳॏΈΛઃఆ͢Δ
-FBLZ6OJUTBOE0UIFS4USBUFHJFTGPS.VMUJQMF5JNF4DBMF w աڈͷใΛ͑ΔͨΊͷ "EEJOH4LJQ$POOFDUJPOTUISPVHI5JNF w ޯͷফࣦͷ͕͘ͳΔ w രൃݩͷ3//ͱಉ͡Ͱൃੜ͢Δ
-FBLZ6OJUTBOEB4QFDUSVNPG%J⒎FSFOU5JNF4DBMFT w աڈͷใΛͲͷఔ͔͢Λ੍ޚ͢Δ 3FNPWJOH$POOFDUJPOT w ͍࣌ࠁͰͷґଘΛ͍࣌ࠁͰͷґଘʹஔ͖͑Δ
-FBLZ6OJUT w աڈͷใΛͲͷ͘Β͍͔͢Λௐ͢Δ w ҠಈฏۉͷΑ͏ͳ;Δ·͍Λ͢Δ w Ћ͕େ͖͍ ʹ͍ۙ աڈͷใΛΑΓอଘ͢Δ w
Ћ͕খ͍͞ ʹ͍ۙ աڈͷใΛ͙͢ʹࣺͯΔ w Ћదʹܾఆ͢ΔϋΠύʔύϥϝʔλ µ(t) ↵µ(t 1) + (1 ↵)v(t)
-POH4IPSU5FSN.FNPSZ w ࣗݾϧʔϓΛಋೖ͢Δ͜ͱͰޯ͕ফ͑ʹ͘͘͢Δ IUUQDPMBIHJUIVCJPQPTUT6OEFSTUBOEJOH-45.T 3// -45.
(BUFE3FDVSSFOU6OJUT w ٙ-45.ෳࡶ͗͢ΔͷͰͳ͍͔ʁ w (36-45.ΑΓߴɾ-45.ͱಉͷੑೳ w ͲͪΒ͕ྑ͍͔λεΫʹΑΔ -45. (36
IUUQTJTBBDDIBOHIBVHJUIVCJP-45.BOE(36'PSNVMB4VNNBSZ
ࣜతʹൺֱ͢ΔʢόΠΞεΛແࢹʣ -45. (36 zt = (xtUz + ht 1Wz)
rt = (xtUr + ht 1Wr) ˜ ht = tanh ⇣ xt + Uh + (rt ht 1)Wh ⌘ ht = (1 zt) ht 1 + zt ˜ ht it = (xtUi + ht 1Wi) ft = (xtUf + ht 1Wf ) ot = (xtUo + ht 1Wg) ˜ Ct = tanh (xtUg + ht 1Wg) Ct = (ft Ct 1 + it ˜ Ct) ht = tanh (Ct) ot (36Ͱೖྗήʔτͱ٫ήʔτ͕౷߹͞Ε͍ͯΔ
0QUJNJ[BUJPOGPS-POH5FSN%FQFOEFODJFT w 3//Λϕʔεͱͨ͠χϡʔϥϧωοτϫʔΫͷඍ w ඇৗʹେ͖ͳΛͱΔPS w ඇৗʹখ͞ͳΛͱΔ w ಛʹɼޯ͕ඇৗʹେ͖ͳͱ͖ʹͲ͏͢Εྑ͍͔ʁ
ޯͷΫϦοϐϯά ޯͷਖ਼نԽ
$MJQQJOH(SBEJFOU w ޯ͕ඇৗʹ େ͖͍cখ͍͞ ͱʁ w ͍͍ͩͨฏΒ͚ͩͲͱ͖Ͳ͖֑͕͋Δ IUUQXXXEFFQMFBSOJOHCPPLPSHMFDUVSF@TMJEFTIUNM
$MJQQJOH(SBEJFOU w ޯ๏ϕʔεͷख๏ʹΑΔͱʜ w ֑ͷपΓͰ͕ਧ͖ඈΜͰ͠·͏ ޯരൃ w ޯ͕େ͖͘ͳΓ͗ͨ͢ΒޯͷϊϧϜͰׂΔ w
ޯΛHͱͯ͠ʜ w WϋΠύʔύϥϝʔλ ࣗવݴޠॲཧͩͱ͕ଟ͍ g ( gv ||g|| (||g|| > v) g (otherwise)
3FHVMBSJ[JOHUP&ODPVSBHF*OGPSNBUJPO'MPX w ਖ਼ଇԽ߲Λಋೖ͢Δ͜ͱͰʮJOGPSNBUJPOqPXʯΛଅਐ w ͜ͷ߲ͷܭࢉ͍͕͠ɼۙࣅ͕ఏҊ͞Ε͍ͯΔ w $MJQQJOHͱΈ߹ΘͤΔ͜ͱͰهԱͰ͖Δڑ͕৳ͼΔ ⌦ =
X t ⇣||(rh(t) L) @h(t) @h(t 1) || ||(rh(t) L)|| 1 ⌘2
&YQMJDJU.FNPSZ w χϡʔϥϧωοτϫʔΫʜ w ҉తͳใͷอ࣋ಘҙ w ໌ࣔతͳใ ࣄ࣮ ͷอ࣋ۤख w
໌ࣔతͳใΛอ࣋͠ɼਪʹ׆༻͢Δߏ ʢϫʔΩϯάϝϞϦͷಋೖʣ w .FNPSZ/FUXPSLT w /FVSBM5VSJOH.BDIJOF
"TDIFNBUJDPGBOFUXPSLXJUIBOFYQMJDJUNFNPSZ IUUQXXXEFFQMFBSOJOHCPPLPSHMFDUVSF@TMJEFTIUNM
"TDIFNBUJDPGBOFUXPSLXJUIBOFYQMJDJUNFNPSZ w ਖ਼֬ͳϝϞϦͷΞυϨεΛग़ྗ͢Δͷ͍͠ w ଟ͘ͷϝϞϦηϧͷॏΈ͖ฏۉΛͱΔ w ॏΈιϑτϚοΫεͳͲͰ࡞Δ ʢͰ͖Δ͚ͩҰՕॴͷϝϞϦΛࢀর͢ΔΑ͏ʹʣ w ϝϞϦηϧεΧϥΑΓϕΫτϧͷํ͕ྑ͍
w ίϯςϯπϕʔεΞυϨογϯά͕ՄೳʹͳΔ w ʮl8FBMMMJWFJOBZFMMPXTVCNBSJOFzΛؚΉՎࢺΛݟ͚ͭΔʯ w ʢϩέʔγϣϯϕʔεΞυϨογϯάͱʁʣ w ʮεϩοτ347ʹ֨ೲ͞Ε͍ͯΔՎࢺΛऔಘ͢Δʯ w ʢΞυϨογϯάΞςϯγϣϯͱಉ͡ܗࣜʣ