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
430
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
680
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
92
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
590
Other Decks in Science
See All in Science
学術講演会中央大学学員会府中支部
tagtag
PRO
0
340
白金鉱業Vol.21【初学者向け発表枠】身近な例から学ぶ数理最適化の基礎 / Learning the Basics of Mathematical Optimization Through Everyday Examples
brainpadpr
1
550
デジタルアーカイブの教育利用促進を目指したメタデータLOD基盤に関する研究 / Research on a Metadata LOD Platform for Promoting Educational Uses of Digital Archives
masao
0
140
[Paper Introduction] From Bytes to Ideas:Language Modeling with Autoregressive U-Nets
haruumiomoto
0
180
データベース05: SQL(2/3) 結合質問
trycycle
PRO
0
870
baseballrによるMLBデータの抽出と階層ベイズモデルによる打率の推定 / TokyoR118
dropout009
2
650
Algorithmic Aspects of Quiver Representations
tasusu
0
160
生成検索エンジン最適化に関する研究の紹介
ynakano
2
1.5k
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
PRO
0
170
AIによる科学の加速: 各領域での革新と共創の未来
masayamoriofficial
0
380
知能とはなにかーヒトとAIのあいだー
tagtag
PRO
0
170
Celebrate UTIG: Staff and Student Awards 2025
utig
0
570
Featured
See All Featured
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
baasie
0
430
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.6k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
16
1.8k
How to Think Like a Performance Engineer
csswizardry
28
2.4k
Introduction to Domain-Driven Design and Collaborative software design
baasie
1
560
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
420
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
1.8k
Side Projects
sachag
455
43k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
61
48k
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.2k
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
0
90
Leadership Guide Workshop - DevTernity 2021
reverentgeek
1
180
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/