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
180
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
420
Firebase-React-App
izuna385
0
260
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.7k
UseCase of Entity Linking
izuna385
0
600
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
670
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
900
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
1.1k
Entity representation with relational attention
izuna385
0
89
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
580
Other Decks in Science
See All in Science
機械学習 - SVM
trycycle
PRO
1
920
安心・効率的な医療現場の実現へ ~オンプレAI & ノーコードワークフローで進める業務改革~
siyoo
0
410
NDCG is NOT All I Need
statditto
2
2.4k
地質研究者が苦労しながら運用する情報公開システムの実例
naito2000
0
310
2025-05-31-pycon_italia
sofievl
0
110
知能とはなにかーヒトとAIのあいだー
tagtag
0
120
会社でMLモデルを作るとは @電気通信大学 データアントレプレナーフェロープログラム
yuto16
1
390
機械学習 - K-means & 階層的クラスタリング
trycycle
PRO
0
1.1k
My Little Monster
juzishuu
0
230
デジタルアーカイブの教育利用促進を目指したメタデータLOD基盤に関する研究 / Research on a Metadata LOD Platform for Promoting Educational Uses of Digital Archives
masao
0
120
データマイニング - グラフデータと経路
trycycle
PRO
1
250
AI(人工知能)の過去・現在・未来 —AIは人間を超えるのか—
tagtag
1
200
Featured
See All Featured
Six Lessons from altMBA
skipperchong
29
4.1k
Code Review Best Practice
trishagee
72
19k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
11
940
Practical Orchestrator
shlominoach
190
11k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
130k
Building a Modern Day E-commerce SEO Strategy
aleyda
45
8.1k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
35
3.2k
How STYLIGHT went responsive
nonsquared
100
5.9k
We Have a Design System, Now What?
morganepeng
54
7.9k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
22k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
34
2.5k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/