Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
DeepNLP_BackPropagation_Rnn_and_Cnn
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
izuna385
July 02, 2018
Science
210
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
490
Firebase-React-App
izuna385
0
290
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
680
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
740
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
130
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
650
Other Decks in Science
See All in Science
機械学習 - ニューラルネットワーク入門
trycycle
PRO
0
1.4k
J-STAGE全文XML登載必須化について
xspa2012
0
1.6k
[Relay webinaire eBIS actu n°16] Amélioration de la survie des JB avec la génétique - Introduction
institutdelelevage
PRO
0
390
AI(人工知能)の過去・現在・未来 ~AIは人類を越えるのか~
tagtag
PRO
0
170
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
1.8k
勾配流から乖離した学習ダイナミクス
hanbao
1
1.1k
白金鉱業Meetup Vol.25 【初学者向け発表枠】「で、この施策って効いてるの」に答える効果検証の基礎 ~ATE / ATT / CATE / LATEを現場の問いに翻訳する~
brainpadpr
1
370
AWS WAFのAIトラフィック収益化機能を考えてみる_20260626
masakiokuda
1
110
AI Agents for Earth Observation
sabman
0
110
データベース05: SQL(2/3) 結合質問
trycycle
PRO
0
1.4k
はじめてのグラフ信号サンプリング
arthur1
0
140
ssmonline #51 ヤマサキ春のサメ祭り 2026 / ssmjp Yamasaki Spring JAWS Festival 2026
naospon
1
170
Featured
See All Featured
Building Better People: How to give real-time feedback that sticks.
wjessup
371
20k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
570
Faster Mobile Websites
deanohume
310
32k
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
33
5.3k
Code Reviewing Like a Champion
maltzj
529
40k
[SF Ruby Conf 2025] Rails X
palkan
3
1.5k
Are puppies a ranking factor?
jonoalderson
2
4.1k
Design of three-dimensional binary manipulators for pick-and-place task avoiding obstacles (IECON2024)
konakalab
0
630
Building a Modern Day E-commerce SEO Strategy
aleyda
45
9.3k
Effective software design: The role of men in debugging patriarchy in IT @ Voxxed Days AMS
baasie
1
570
Being A Developer After 40
akosma
92
590k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/