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
0
190
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
Tweet
Share
More Decks by izuna385
See All by izuna385
jel: japanese entity linker
izuna385
0
440
Firebase-React-App
izuna385
0
260
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
610
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
690
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
910
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
95
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
590
Other Decks in Science
See All in Science
Accelerated Computing for Climate forecast
inureyes
PRO
0
150
Collective Predictive Coding as a Unified Theory for the Socio-Cognitive Human Minds
tanichu
0
160
安心・効率的な医療現場の実現へ ~オンプレAI & ノーコードワークフローで進める業務改革~
siyoo
0
460
データベース05: SQL(2/3) 結合質問
trycycle
PRO
0
880
20251212_LT忘年会_データサイエンス枠_新川.pdf
shinpsan
0
230
動的トリートメント・レジームを推定するDynTxRegimeパッケージ
saltcooky12
0
250
データベース09: 実体関連モデル上の一貫性制約
trycycle
PRO
0
1.1k
あなたに水耕栽培を愛していないとは言わせない
mutsumix
1
250
コンピュータビジョンによるロボットの視覚と判断:宇宙空間での適応と課題
hf149
1
530
Vibecoding for Product Managers
ibknadedeji
0
130
NDCG is NOT All I Need
statditto
2
2.8k
生成検索エンジン最適化に関する研究の紹介
ynakano
2
2k
Featured
See All Featured
From π to Pie charts
rasagy
0
130
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
aleyda
2
9.6k
Navigating Team Friction
lara
192
16k
Test your architecture with Archunit
thirion
1
2.2k
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
2
420
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.7k
The browser strikes back
jonoalderson
0
390
Agile that works and the tools we love
rasmusluckow
331
21k
Public Speaking Without Barfing On Your Shoes - THAT 2023
reverentgeek
1
310
The Director’s Chair: Orchestrating AI for Truly Effective Learning
tmiket
1
98
What's in a price? How to price your products and services
michaelherold
247
13k
RailsConf 2023
tenderlove
30
1.3k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/