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
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
470
Firebase-React-App
izuna385
0
270
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
650
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
980
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
110
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
630
Other Decks in Science
See All in Science
検索と推論タスクに関する論文の紹介
ynakano
1
250
データベース05: SQL(2/3) 結合質問
trycycle
PRO
0
1.2k
Conversation is the New Dashboard: 属人性を排除する第4世代BIツールの勢力図
shomaekawa
1
610
Testing the Longevity Bottleneck Hypothesis
chinson03
0
370
データベース01: データベースを使わない世界
trycycle
PRO
1
1.3k
Cross-Media Technologies, Information Science and Human-Information Interaction
signer
PRO
3
32k
Distributional Regression
tackyas
0
550
機械学習 - ニューラルネットワーク入門
trycycle
PRO
0
1.1k
20260220 OpenIDファウンデーション・ジャパン ご紹介 / 20260220 OpenID Foundation Japan Intro
oidfj
0
370
大黒市で発生した大規模インシデント の ポストモーテムから読み解く、 記憶媒体消去の大切さ
shucho0103
0
200
[NLP2026 参加報告会] AI for Science まとめ / NLP2026
lychee1223
0
1.9k
【論文紹介】Is CLIP ideal? No. Can we fix it?Yes! 第65回 コンピュータビジョン勉強会@関東
shun6211
5
2.5k
Featured
See All Featured
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
11
970
Leo the Paperboy
mayatellez
8
1.9k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
3.7k
Impact Scores and Hybrid Strategies: The future of link building
tamaranovitovic
0
330
WENDY [Excerpt]
tessaabrams
11
38k
Color Theory Basics | Prateek | Gurzu
gurzu
0
390
ラッコキーワード サービス紹介資料
rakko
1
3.9M
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.2k
How To Speak Unicorn (iThemes Webinar)
marktimemedia
1
500
Paper Plane (Part 1)
katiecoart
PRO
0
9.6k
What the history of the web can teach us about the future of AI
inesmontani
PRO
1
630
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/