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
140
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
300
Firebase-React-App
izuna385
0
220
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.5k
UseCase of Entity Linking
izuna385
0
500
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
630
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
740
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
960
Entity representation with relational attention
izuna385
0
74
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
500
Other Decks in Science
See All in Science
Celebrate UTIG: Staff and Student Awards 2024
utig
0
460
Mechanistic Interpretability の紹介
sohtakahashi
0
350
HAS Dark Site Orientation
astronomyhouston
0
5.3k
『データ可視化学入門』を PythonからRに翻訳した話
bob3bob3
1
500
Pericarditis Comic
camkdraws
0
1.2k
【健康&筋肉と生産性向上の関連性】 【Google Cloudを企業で運用する際の知識】 をお届け
yasumuusan
0
330
[第62回 CV勉強会@関東] Long-CLIP: Unlocking the Long-Text Capability of CLIP / kantoCV 62th ECCV 2024
lychee1223
1
670
Sociovirology
uni_of_nomi
0
100
解説!データ基盤の進化を後押しする手順とタイミング
shomaekawa
1
340
私たちのプロダクトにとってのよいテスト/good test for our products
camel_404
0
180
ベイズ最適化をゼロから
brainpadpr
2
810
Machine Learning for Materials (Lecture 8)
aronwalsh
0
410
Featured
See All Featured
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
720
Making Projects Easy
brettharned
115
5.9k
It's Worth the Effort
3n
183
27k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
48k
Statistics for Hackers
jakevdp
796
220k
Fashionably flexible responsive web design (full day workshop)
malarkey
405
65k
What's in a price? How to price your products and services
michaelherold
243
12k
Bootstrapping a Software Product
garrettdimon
PRO
305
110k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
16
2.1k
4 Signs Your Business is Dying
shpigford
180
21k
Agile that works and the tools we love
rasmusluckow
327
21k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
28
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/