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
NFNet
Search
kazukim10
February 18, 2021
47
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
NFNet
I summarize NFNet.
kazukim10
February 18, 2021
More Decks by kazukim10
See All by kazukim10
Sprint16論文紹介
kazukim10
0
100
Featured
See All Featured
Being A Developer After 40
akosma
92
590k
Build The Right Thing And Hit Your Dates
maggiecrowley
39
3.5k
Rebuilding a faster, lazier Slack
samanthasiow
85
9.7k
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
aleyda
2
2.2k
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
460
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.8k
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4.2k
The agentic SEO stack - context over prompts
schlessera
0
970
B2B Lead Gen: Tactics, Traps & Triumph
marketingsoph
1
280
Statistics for Hackers
jakevdp
799
230k
Highjacked: Video Game Concept Design
rkendrick25
PRO
1
480
BBQ
matthewcrist
90
10k
Transcript
どんなもの? 先行研究と比べて何がすごい? 技術の手法や肝は? 議論はある? どうやって有効だと検証した? 次に読むべき論文は? ・AGC(adaptive gradient Clipping) ・NF-ResNets
・AGCを使って、バッチノームレイヤー無しのモデルをトレーニングできた。 ・このモデルは、accuracy、訓練速度において他のモデルを上回った。 ・バッチノーマライゼーションのメリットを残して、 デメリットを無くす代替手法(ネットワーク構造)の提案 High-Performance Large-Scale Image Recognition Without Normalization (2021) Andrew Brock/Soham De/Samuel L. Smith/Karen Simonyan DeepMind ・ImageNetを使って他のモデルと精度(accuracy)と、トレーニング速度を比較 ・BatchNormalization ・ResNet