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
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
930
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
99
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
600
Other Decks in Science
See All in Science
Distributional Regression
tackyas
0
450
NDCG is NOT All I Need
statditto
2
3k
Non-Gaussian, nonlinear causal discovery with hidden variables and application
sshimizu2006
0
100
ハミルトン・ヤコビ方程式の解の性質と物理的意味
enakai00
0
170
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
460
ド文系だった私が、 KaggleのNCAAコンペでソロ金取れるまで
wakamatsu_takumu
2
2.2k
DMMにおけるABテスト検証設計の工夫
xc6da
1
1.7k
データマイニング - ノードの中心性
trycycle
PRO
0
360
人生を変えた一冊「独学大全」のはなし / Self-study ENCYCLOPEDIA: The Book Which Change My Life #独学大全 #EM推し本
expajp
0
140
データベース10: 拡張実体関連モデル
trycycle
PRO
0
1.1k
生成AIの現状と展望
tagtag
PRO
0
110
データマイニング - グラフ埋め込み入門
trycycle
PRO
1
200
Featured
See All Featured
Abbi's Birthday
coloredviolet
2
6.2k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.2k
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
1.9k
GraphQLの誤解/rethinking-graphql
sonatard
75
12k
A Tale of Four Properties
chriscoyier
163
24k
Crafting Experiences
bethany
1
100
Building Applications with DynamoDB
mza
96
7k
Why Our Code Smells
bkeepers
PRO
340
58k
Highjacked: Video Game Concept Design
rkendrick25
PRO
1
340
How to Talk to Developers About Accessibility
jct
2
170
So, you think you're a good person
axbom
PRO
2
2k
Designing Experiences People Love
moore
143
24k
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 : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/