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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
izuna385
July 02, 2018
Science
190
0
Share
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
460
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
630
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
710
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
950
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
100
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
610
Other Decks in Science
See All in Science
【RSJ2025】PAMIQ Core: リアルタイム継続学習のための⾮同期推論・学習フレームワーク
gesonanko
0
830
やるべきときにMLをやる AIエージェント開発
fufufukakaka
2
1.4k
My Little Monster
juzishuu
0
700
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
320
アクシズを探せ! 各勢力の位置関係についての考察
miu_crescent
PRO
1
270
KISHIMOTO Atsuo
genomethica
0
130
因果推論と機械学習
sshimizu2006
1
1.1k
Question Driven Development using Python
willingc
PRO
1
110
2026 Design Informatics 01: Introduction
kanaya
0
110
Distributional Regression
tackyas
0
480
HDC tutorial
michielstock
2
650
タンパク質間相互作⽤を利⽤した⼈⼯知能による新しい薬剤遺伝⼦-疾患相互作⽤の同定
tagtag
PRO
0
200
Featured
See All Featured
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
290
How to make the Groovebox
asonas
2
2.2k
Marketing to machines
jonoalderson
1
5.2k
Leo the Paperboy
mayatellez
7
1.8k
Bootstrapping a Software Product
garrettdimon
PRO
307
120k
Site-Speed That Sticks
csswizardry
13
1.2k
What the history of the web can teach us about the future of AI
inesmontani
PRO
1
550
Ten Tips & Tricks for a 🌱 transition
stuffmc
0
110
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
210
Art, The Web, and Tiny UX
lynnandtonic
304
21k
Product Roadmaps are Hard
iamctodd
PRO
55
12k
New Earth Scene 8
popppiees
3
2.2k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/