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
150
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
330
Firebase-React-App
izuna385
0
230
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.6k
UseCase of Entity Linking
izuna385
0
530
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
640
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
800
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
1k
Entity representation with relational attention
izuna385
0
75
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
530
Other Decks in Science
See All in Science
学術講演会中央大学学員会いわき支部
tagtag
0
130
Pericarditis Comic
camkdraws
0
1.5k
Machine Learning for Materials (Challenge)
aronwalsh
0
100
Tensor Representations in Signal Processing and Machine Learning (Tutorial at APSIPA-ASC 2020)
yokotatsuya
0
110
Design of three-dimensional binary manipulators for pick-and-place task avoiding obstacles (IECON2024)
konakalab
0
130
3次元点群を利用した植物の葉の自動セグメンテーションについて
kentaitakura
2
880
学術講演会中央大学学員会八王子支部
tagtag
0
270
Trend Classification of InSAR Displacement Time Series Using SAE–CNN
satai
2
130
Healthcare Innovation through Business Entrepreneurship
clintwinters
0
190
小杉考司(専修大学)
kosugitti
2
610
LIMEを用いた判断根拠の可視化
kentaitakura
0
430
FOGBoston2024
lcolladotor
0
150
Featured
See All Featured
Typedesign – Prime Four
hannesfritz
40
2.5k
Embracing the Ebb and Flow
colly
84
4.6k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
45
9.4k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
Gamification - CAS2011
davidbonilla
80
5.1k
Adopting Sorbet at Scale
ufuk
74
9.2k
Measuring & Analyzing Core Web Vitals
bluesmoon
6
240
Designing on Purpose - Digital PM Summit 2013
jponch
117
7.1k
We Have a Design System, Now What?
morganepeng
51
7.4k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
12
960
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
44
7k
The MySQL Ecosystem @ GitHub 2015
samlambert
250
12k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/