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
DeepNLP_BackPropagation_Rnn_and_Cnn
Search
izuna385
July 02, 2018
Science
200
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
DeepNLP_BackPropagation_Rnn_and_Cnn
深層学習による自然言語処理 2.5から2.9まで
izuna385
July 02, 2018
More Decks by izuna385
See All by izuna385
jel: japanese entity linker
izuna385
0
480
Firebase-React-App
izuna385
0
280
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.8k
UseCase of Entity Linking
izuna385
0
660
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
720
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
1k
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
1.2k
Entity representation with relational attention
izuna385
0
120
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
630
Other Decks in Science
See All in Science
AIを用いた PID制御で部屋 の温度制御をしてみた
nearme_tech
PRO
0
230
ssmonline #51 ヤマサキ春のサメ祭り 2026 / ssmjp Yamasaki Spring JAWS Festival 2026
naospon
1
130
Conwayの法則を"ちゃんと"使うために — 原典でConwayは何を言っていたのか
bonotake
10
6.7k
20260410_SystemsThinking
takusamar
1
150
Conversation is the New Dashboard: 属人性を排除する第4世代BIツールの勢力図
shomaekawa
1
640
AlgorithAlgorihms for Decision Making
mickey_kubo
0
130
データベース01: データベースを使わない世界
trycycle
PRO
1
1.5k
データベース06: SQL (3/3) 副問い合わせ
trycycle
PRO
1
1.1k
データベース12: 正規化(2/2) - データ従属性に基づく正規化
trycycle
PRO
0
1.7k
Massey Ratings for Match Outcome Prediction in Table Tennis: Evidence of Greater Stability than the ITTF World Ranking
konakalab
0
130
20260220 OpenIDファウンデーション・ジャパン ご紹介 / 20260220 OpenID Foundation Japan Intro
oidfj
PRO
0
400
サンプル対応のない複数遺伝子発現プロファイルに対するテンソル分解型統合解析の要約
tagtag
PRO
0
240
Featured
See All Featured
How GitHub (no longer) Works
holman
316
150k
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.8k
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
180
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
Intergalactic Javascript Robots from Outer Space
tanoku
273
27k
Build your cross-platform service in a week with App Engine
jlugia
234
19k
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
6
1.2k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
2k
Site-Speed That Sticks
csswizardry
13
1.5k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
3k
Speed Design
sergeychernyshev
33
2k
Transcript
5 . 1 2
• : D !(#) 1 ∇!(#) • L 1 )
) ( 1 S G G 1 & '()*+, = .(/ 012 .(⋯ .(/ 2 '()*+, + 5(2)))) 62 67 68 69 /(:) ⋯ ⋯ ⋯ ⋯ ⋯ ⋯ ;2 ;7 /(:<2) = − 1 = = + 1
. . ! ℎ($) ℎ(&) ℎ(') (($) ((&) ((') ℎ(')=
( ' ( & ( $ ! *+(,) *- = *+(,) *.(/) 0 *.(/) *.(1) 0 *.(1) *- •
. . ! ℎ($) ℎ(&) '($) '(&)
. .
None
(
.( )
( )
2'+ )NN 2 #) 0%&1&-" (3*, )
.( !/$→ → Residual Connection, Batch Nomalization( ) ! Loss func ! Loss func
: Residual Connection –– F(x) (→-!()) F(x) + x
→ & " - Identity Mapping ' : -*&%,+' ./$ # Identity – [1] He, Kaiming, et al. "Identity mappings in deep residual networks." European Conference on Computer Vision. Springer, Cham, 2016. . .
. . (2.33) (2.34)
0 1 . 2 C2 2 " 3 2 3
2 ) 2 2 ( 3 23 2 !"#$ !" %"&$ %"#$ %" %"&$ '() '() '() '*+, '*+, -"#$ = /(!"#$ ) -" -"&$ %" !" M I NR 2 '*+, O L '() : input P / L !" = '*+, 2 !"#$ + '() %" ,, L
2 . 3 !" #$% &% !" #$' !" #$(
!% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )(
2 . 3 !" #$% &% !" #$' !" #$(
!% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )(
2 . 3 !" #$% &% !" #$' !" #$(
!% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )(
2 . 3 !" #$% &% !" #$' !" #$(
!% #$% !% #$' !% #$( !' #$% !' #$' !' #$( !( #$% !( #$' !( #$( &' &( )% )' )( • 23 !* # 1
: !"#$ !%& '( )( … … )*
'* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/
. - •
) (
8 99 2 :9.8 9 9 6 5 3 2
2 5 2 28 79 8 3 9 1 56 2 59 7 /0-
-5 1 02 1 25 58 8 ./ 8 .2
0 8
22/1 444 1 1 - 2 3--.-.3-. 11
http://deeplearning.stanford.edu/wiki/index .php/Feature_extraction_using_convolution
/885 6 0: 6. 5 5
RNN Vanishing/Exploding Gradient : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/