Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
DeepNLP_BackPropagation_Rnn_and_Cnn
Search
izuna385
July 02, 2018
Science
210
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
500
Firebase-React-App
izuna385
0
290
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
680
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
750
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
1k
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
140
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
650
Other Decks in Science
See All in Science
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
1.8k
機械学習 - SVM
trycycle
PRO
2
1.3k
CVPR2026_VGGTとその仲間たち
mickey_0226
0
1.3k
知能とはなにか -ヒトとAIのあいだ-
tagtag
PRO
0
170
プレイがつなぐ研究と社会:市⺠‧クリエイター‧SF作家による実践を通じて
hayataka88
1
140
因果探索の発展と展望
sshimizu2006
2
1.3k
[Relay webinaire eBIS actu n°16] Sélection pour la vitalité des jeunes bovins allaitants et laitiers
institutdelelevage
PRO
0
350
Leitner Inauguration Lecture Chalmers University of Technology
xleitix
0
410
J-STAGE全文XML登載必須化について
xspa2012
0
1.7k
[Relay webinaire eBIS actu n°16] Conclusion
institutdelelevage
PRO
0
300
第67回コンピュータビジョン勉強会論文紹介「RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning」
x_ttyszk
0
260
自社のレビュー履歴からAIコードレビュアーをつくる方法
estie
5
1.9k
Featured
See All Featured
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
23k
Building an army of robots
kneath
307
47k
How to make the Groovebox
asonas
2
2.5k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
610
How to build an LLM SEO readiness audit: a practical framework
nmsamuel
2
970
Agile Actions for Facilitating Distributed Teams - ADO2019
mkilby
0
330
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
56
3.5k
The Anti-SEO Checklist Checklist. Pubcon Cyber Week
ryanjones
0
290
Designing Experiences People Love
moore
143
24k
Large-scale JavaScript Application Architecture
addyosmani
516
110k
End of SEO as We Know It (SMX Advanced Version)
ipullrank
3
4.5k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.6k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/