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
200
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
480
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
660
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
720
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
990
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
120
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
630
Other Decks in Science
See All in Science
データベース03: 関係データモデル
trycycle
PRO
1
790
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
150
データベース08: 実体関連モデルとは?
trycycle
PRO
0
1.6k
AkarengaLT vol.40
hashimoto_kei
0
120
Conversation is the New Dashboard: 属人性を排除する第4世代BIツールの勢力図
shomaekawa
1
630
データベース09: 実体関連モデル上の一貫性制約
trycycle
PRO
0
1.8k
How a camera trap data standard enabled an ecosystem of interoperable tools
peterdesmet
0
110
機械学習 - DBSCAN
trycycle
PRO
0
2k
プロジェクト「Azayaka」のSARの数式とジオメトリ
syuchimu
0
430
因果探索の発展と展望
sshimizu2006
2
850
Sstニューロンによる睡眠不足と回復の制御:データ駆動型トランスクリプトーム解析
tagtag
PRO
0
120
データベース01: データベースを使わない世界
trycycle
PRO
1
1.4k
Featured
See All Featured
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
1
370
Digital Projects Gone Horribly Wrong (And the UX Pros Who Still Save the Day) - Dean Schuster
uxyall
1
2.3k
How to Align SEO within the Product Triangle To Get Buy-In & Support - #RIMC
aleyda
2
1.8k
HTML-Aware ERB: The Path to Reactive Rendering @ RubyCon 2026, Rimini, Italy
marcoroth
3
430
Navigating the moral maze — ethical principles for Al-driven product design
skipperchong
2
490
Producing Creativity
orderedlist
PRO
348
40k
Marketing Yourself as an Engineer | Alaka | Gurzu
gurzu
0
280
Into the Great Unknown - MozCon
thekraken
41
2.7k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
16
2.1k
End of SEO as We Know It (SMX Advanced Version)
ipullrank
3
4.4k
Visualization
eitanlees
152
17k
Code Review Best Practice
trishagee
74
20k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/