$30 off During Our Annual Pro Sale. View Details »
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
420
Firebase-React-App
izuna385
0
260
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
600
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
900
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
89
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
580
Other Decks in Science
See All in Science
研究って何だっけ / What is Research?
ks91
PRO
2
160
凸最適化からDC最適化まで
santana_hammer
1
330
MCMCのR-hatは分散分析である
moricup
0
520
DMMにおけるABテスト検証設計の工夫
xc6da
1
1.4k
あなたに水耕栽培を愛していないとは言わせない
mutsumix
0
120
データマイニング - グラフデータと経路
trycycle
PRO
1
250
My Little Monster
juzishuu
0
280
Rashomon at the Sound: Reconstructing all possible paleoearthquake histories in the Puget Lowland through topological search
cossatot
0
140
主成分分析に基づく教師なし特徴抽出法を用いたコラーゲン-グリコサミノグリカンメッシュの遺伝子発現への影響
tagtag
0
110
ランサムウェア対策にも考慮したVMware、Hyper-V、Azure、AWS間のリアルタイムレプリケーション「Zerto」を徹底解説
climbteam
0
170
風の力で振れ幅が大きくなる振り子!? 〜タコマナローズ橋はなぜ落ちたのか〜
syotasasaki593876
1
150
Agent開発フレームワークのOverviewとW&B Weaveとのインテグレーション
siyoo
0
390
Featured
See All Featured
A better future with KSS
kneath
240
18k
Java REST API Framework Comparison - PWX 2021
mraible
34
9k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.5k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
15k
Statistics for Hackers
jakevdp
799
230k
Facilitating Awesome Meetings
lara
57
6.7k
Agile that works and the tools we love
rasmusluckow
331
21k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
253
22k
[RailsConf 2023] Rails as a piece of cake
palkan
58
6.1k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Why You Should Never Use an ORM
jnunemaker
PRO
60
9.6k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
35
2.3k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/