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
izuna385
July 02, 2018
Science
200
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
480
Firebase-React-App
izuna385
0
280
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
660
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
720
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
120
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
640
Other Decks in Science
See All in Science
Wet Active Matter
rajeshrinet
0
150
生成AI・プレプリント時代における 研究成果公開の再設計 ― トップカンファレンス文化はどこへ向かうのか / Redesigning the Dissemination of Research Outputs in the Age of Generative AI and Preprints — Where Is the Top-Conference Culture Heading?
ykiyota
0
30k
「遂行理論の未来」(松島斉教授最終講義記念セッションの発表資料)
shunyanoda
0
990
機械学習 - K近傍法 & 機械学習のお作法
trycycle
PRO
1
1.6k
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
1.7k
サンプル対応のない複数遺伝子発現プロファイルに対するテンソル分解型統合解析の要約
tagtag
PRO
0
250
水耕栽培を始める前に知っておきたい植物の科学
grow_design_lab
0
350
共生概念の整理と AIアライメントの構想
hiroakihamada
0
280
データベース03: 関係データモデル
trycycle
PRO
1
820
機械学習 - DBSCAN
trycycle
PRO
0
2.1k
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
1.7k
不動産業界における業界特化のデータ整備とAI活用 ─Vertical DataとVertical AI─
estie
1
960
Featured
See All Featured
For a Future-Friendly Web
brad_frost
183
10k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3.4k
Bioeconomy Workshop: Dr. Julius Ecuru, Opportunities for a Bioeconomy in West Africa
akademiya2063
PRO
1
350
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.5k
Prompt Engineering for Job Search
mfonobong
0
450
Color Theory Basics | Prateek | Gurzu
gurzu
0
460
エンジニアに許された特別な時間の終わり
watany
108
250k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
Game over? The fight for quality and originality in the time of robots
wayneb77
1
270
sira's awesome portfolio website redesign presentation
elsirapls
0
410
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
23k
Tips & Tricks on How to Get Your First Job In Tech
honzajavorek
1
730
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/