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
180
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
380
Firebase-React-App
izuna385
0
250
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.7k
UseCase of Entity Linking
izuna385
0
580
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
670
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
880
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
1.1k
Entity representation with relational attention
izuna385
0
84
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
570
Other Decks in Science
See All in Science
研究って何だっけ / What is Research?
ks91
PRO
1
120
mathematics of indirect reciprocity
yohm
1
180
How To Buy, Verified Venmo Accounts in 2025 This year
usaallshop68
4
270
データマイニング - ノードの中心性
trycycle
PRO
0
270
データベース14: B+木 & ハッシュ索引
trycycle
PRO
0
450
CV_5_3dVision
hachama
0
150
機械学習 - DBSCAN
trycycle
PRO
0
1k
データから見る勝敗の法則 / The principle of victory discovered by science (open lecture in NSSU)
konakalab
1
150
白金鉱業Meetup Vol.16_数理最適化案件のはじめかた・すすめかた
brainpadpr
4
2k
Symfony Console Facelift
chalasr
2
470
テンソル分解による糖尿病の組織特異的遺伝子発現の統合解析を用いた関連疾患の予測
tagtag
2
240
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
970
Featured
See All Featured
Speed Design
sergeychernyshev
32
1.1k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
Building an army of robots
kneath
306
46k
Practical Orchestrator
shlominoach
190
11k
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
112
20k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Embracing the Ebb and Flow
colly
87
4.8k
Build The Right Thing And Hit Your Dates
maggiecrowley
37
2.9k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
51
5.6k
Rails Girls Zürich Keynote
gr2m
95
14k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
126
53k
Producing Creativity
orderedlist
PRO
347
40k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/