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
180
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
440
RoBERTa: paper reading
himkt
1
320
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
500
Interpretable Machine Learning 6.3 - Prototypes and Criticisms
himkt
2
150
ニューラル固有表現抽出 / Neural Named Entity Recognition
himkt
3
690
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
コーパスを丸呑みしたモデルから言語の何がわかるか
eumesy
PRO
9
2.6k
Data-centric AI勉強会 「ロボットにおけるData-centric AI」
haraduka
0
480
医療支援AI開発における臨床と情報学の連携を円滑に進めるために
moda0
0
150
非ガウス性と非線形性に基づく統計的因果探索
sshimizu2006
0
560
知識強化言語モデルLUKE @ LUKEミートアップ
ikuyamada
0
260
A Segment Anything Model based weakly supervised learning method for crop mapping using Sentinel-2 time series images
satai
3
140
【NLPコロキウム】Stepwise Alignment for Constrained Language Model Policy Optimization (NeurIPS 2024)
akifumi_wachi
3
540
PhD Defence: Considering Temporal and Contextual Information for Lexical Semantic Change Detection
a1da4
0
130
Retrieval of Hurricane Rain Rate From SAR Images Based on Artificial Neural Network
satai
3
150
2038年問題が思ったよりヤバい。検出ツールを作って脅威性評価してみた論文 | Kansai Open Forum 2024
ran350
8
3.9k
Weekly AI Agents News! 12月号 論文のアーカイブ
masatoto
0
200
한국어 오픈소스 거대 언어 모델의 가능성: 새로운 시대의 언어 이해와 생성
inureyes
PRO
0
230
Featured
See All Featured
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
656
59k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
28
9.3k
Side Projects
sachag
452
42k
The Power of CSS Pseudo Elements
geoffreycrofte
75
5.5k
A Philosophy of Restraint
colly
203
16k
Why Our Code Smells
bkeepers
PRO
336
57k
Statistics for Hackers
jakevdp
797
220k
Docker and Python
trallard
44
3.3k
Product Roadmaps are Hard
iamctodd
PRO
51
11k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
40
2k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
27
1.6k
Imperfection Machines: The Place of Print at Facebook
scottboms
267
13k
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