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
Problems of Neural Networks and its solutions
Search
izuna385
June 21, 2018
Technology
0
130
Problems of Neural Networks and its solutions
Residual Connections とBatch Normalizationがメイン
izuna385
June 21, 2018
Tweet
Share
More Decks by izuna385
See All by izuna385
jel: japanese entity linker
izuna385
0
330
Firebase-React-App
izuna385
0
230
React+FastAPIを用いた簡単なWebアプリ作製
izuna385
0
1.6k
UseCase of Entity Linking
izuna385
0
540
Unofficial slides: From Zero to Hero: Human-In-The-Loop Entity Linking in Low Resource Domains (ACL 2020)
izuna385
1
650
Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
izuna385
0
830
Zero-shot Entity Linking with Dense Entity Retrieval (Unofficial slides) and Entity Linking future directions
izuna385
3
1k
Entity representation with relational attention
izuna385
0
80
Zero-Shot Entity Linking by Reading Entity Descriptions
izuna385
0
540
Other Decks in Technology
See All in Technology
10分でわかるfreeeのQA
freee
1
12k
テキスト解析で見る PyCon APAC 2025 セッション&スピーカートレンド分析
negi111111
0
270
YOLOv10~v12
tenten0727
3
670
LLM とプロンプトエンジニアリング/チューターをビルドする / LLM, Prompt Engineering and Building Tutors
ks91
PRO
1
200
OPENLOGI Company Profile
hr01
0
62k
Cline、めっちゃ便利、お金が飛ぶ💸
iwamot
PRO
22
19k
「家族アルバム みてね」を支えるS3ライフサイクル戦略
fanglang
4
640
Automatically generating types by running tests
sinsoku
1
200
AIエージェントキャッチアップと論文リサーチ
os1ma
6
1.4k
SREの視点で考えるSIEM活用術 〜AWS環境でのセキュリティ強化〜
coconala_engineer
1
220
はてなの開発20年史と DevOpsの歩み / DevOpsDays Tokyo 2025 Keynote
daiksy
5
1.2k
「それはhowなんよ〜」のガイドライン #orestudy
77web
9
2.4k
Featured
See All Featured
Making Projects Easy
brettharned
116
6.1k
Into the Great Unknown - MozCon
thekraken
36
1.7k
Documentation Writing (for coders)
carmenintech
69
4.7k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
251
21k
Art, The Web, and Tiny UX
lynnandtonic
298
20k
VelocityConf: Rendering Performance Case Studies
addyosmani
328
24k
Git: the NoSQL Database
bkeepers
PRO
430
65k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
Side Projects
sachag
452
42k
A designer walks into a library…
pauljervisheath
205
24k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
177
52k
Transcript
1 / 18 Neural Networks
2 / 18 1. NN !
• Residual Network • Batch Normalization 2. 1. • •
3 / 18 Plain NNs(&) ' pros #%
" (ex. CNN, RNN, ...) cons ! $ $
4 / 18 RNN RNN [1] P. Razvan et
al ,"On the difficulty of training recurrent neural networks." International Conference on Machine Learning. 2013. !"#$ !" %"&$ %"#$ %" %"&$ '() '() '() '*+, '*+, -!"# = /(!!"# ) -! -!$# %! : input !! : hidden state '%&' : '() : input / !" = '*+, 2 !"#$ + '() %"
5 / 18 !" !# !$ %" %# %$ &'(
&'( &'( &)*+ &)*+ ,! = .(!! ) ," ,# RNN 3 1, 12 = 1," 12 + 1,# 12 + 1,$ 12 1,$ 12 = 4 "565$ 1,$ 1!$ 7 1!$ 1!6 7 18!6 12 1!$ 1!" = 1!$ 1!# 7 1!# 1!" = &)*+ 9 :;<= >? !# 7 &)*+ 9 :;<= >? !" @A!B @C : !" ~!6E" fix !6
6 / 18 RNN Vanishing/Exploding Gradient : !"#$ !%&
'( )( … … )* '* ………… ………… +( +* !"#$ (-) !%& (-) '% …… '/ )/ +/
7 / 18 ,$+ /' !"#$ !- !"#$ 2 %
× '()* + ×%,- → # !"#$ !"#$ . 2 % × '()*(+).,-×%,- 1%input or 1)* Loss( RNN ."0& Vanishing/Exploding Gradient
8 / 18 +$ DeepNN( ! +
" )*&!/#% ' (→ ! Loss func ! Loss func → Residual Connection, Batch No malization
9 / 18 0), : Residual Connection – -– F(x)
"/#2 → "/ F(x) + x → (4 '$"/ Identity Mapping +%*1&: 3 . ! 3 Identity – [1] He, Kaiming, et al. "Identity mappings in deep residual networks." European Conference on Computer Vision. Springer, Cham, 2016.
10 / 18 : Residual Connection –– ' Forward
$#& Backward !$"& Deep % & input
11 / 18 Residual Connection –– https://icml.cc/2016/tutorials/icml2016_tutorial_deep_residual_networks_kaiminghe.pdf
12 / 18 ResNet Batch Normalization ResNet Residual Block
• ImplementationBatch Normalization NN ! $# • Batch Normalization" ## http://torch.ch/blog/2016/02/04/resnets.html Plain
13 / 18 ( ) 1 2
( ) n … Batch Normalization –Revisit Gaussian-
14 / 18 Batch Normalization -Input Data distribution
- (Convergence) !! Input NN → input
15 / 18 Batch Normalization -distribution - !"#$% & '
= ) & ' ← ' − , - ~/(,, -2) input
16 / 18 Batch Normalization Data distribution •
=(!, ")fix • Batch Normalization Batch Normalization
17 / 18 Batch Normalization – [2]Ioffe, Sergey,
and Christian Szegedy. "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift." (2015). !, # !%$( → normalize scaling '"&# nomalize
18 / 18 DeepNN+ ! /
& -"#.#)%/'( *$ +!→ , Identity – normalize scaling implement Deep Net