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
190
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
450
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
620
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
700
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
920
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
98
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
600
Other Decks in Science
See All in Science
データマイニング - ウェブとグラフ
trycycle
PRO
0
260
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
180
Testing the Longevity Bottleneck Hypothesis
chinson03
0
190
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
870
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
660
凸最適化からDC最適化まで
santana_hammer
1
370
Kaggle: NeurIPS - Open Polymer Prediction 2025 コンペ 反省会
calpis10000
0
420
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
240
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
120
AkarengaLT vol.41
hashimoto_kei
1
120
AI(人工知能)の過去・現在・未来 —AIは人間を超えるのか—
tagtag
PRO
0
160
力学系から見た現代的な機械学習
hanbao
3
4k
Featured
See All Featured
Typedesign – Prime Four
hannesfritz
42
3k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
16
1.9k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
220
Facilitating Awesome Meetings
lara
57
6.8k
Marketing to machines
jonoalderson
1
5k
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
2
170
Reality Check: Gamification 10 Years Later
codingconduct
0
2k
Testing 201, or: Great Expectations
jmmastey
46
8.1k
Believing is Seeing
oripsolob
1
84
Leading Effective Engineering Teams in the AI Era
addyosmani
9
1.7k
Code Reviewing Like a Champion
maltzj
528
40k
Technical Leadership for Architectural Decision Making
baasie
3
290
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/