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
PaperReading-ExplainingKnowledgeDistillationByQ...
Search
sarrrrry
November 10, 2020
Research
0
35
PaperReading-ExplainingKnowledgeDistillationByQuantifyingTheKnowledge
論文読み会用の(CVPR2020)ExplainingKnowledgeDistillationByQuantifyingTheKnowledgeの発表資料です。
sarrrrry
November 10, 2020
Tweet
Share
More Decks by sarrrrry
See All by sarrrrry
点過程の基礎とその周辺
sarrrrry
0
170
みずほ銀行の2021年大規模システム障害に関する考察
sarrrrry
1
140
CompML : Elementary knowledge for 'Parameter-Free Online Optimization'
sarrrrry
1
120
CompML:PaperReading-PHM-No.1
sarrrrry
0
160
Other Decks in Research
See All in Research
ニューラルネットワークの損失地形
joisino
PRO
36
18k
The many faces of AI and the role of mathematics
gpeyre
1
1.4k
ベイズ的方法に基づく統計的因果推論の基礎
holyshun
0
610
医療支援AI開発における臨床と情報学の連携を円滑に進めるために
moda0
0
120
尺度開発における質的研究アプローチ(自主企画シンポジウム7:認知行動療法における尺度開発のこれから)
litalicolab
0
360
メールからの名刺情報抽出におけるLLM活用 / Use of LLM in extracting business card information from e-mails
sansan_randd
2
270
さんかくのテスト.pdf
sankaku0724
0
520
CoRL2024サーベイ
rpc
1
1.1k
機械学習でヒトの行動を変える
hiromu1996
1
380
Large Vision Language Model (LVLM) に関する最新知見まとめ (Part 1)
onely7
22
4.8k
打率7割を実現する、プロダクトディスカバリーの7つの極意(pmconf2024)
geshi0820
0
130
Weekly AI Agents News! 11月号 プロダクト/ニュースのアーカイブ
masatoto
0
200
Featured
See All Featured
Bootstrapping a Software Product
garrettdimon
PRO
305
110k
Site-Speed That Sticks
csswizardry
2
190
Building an army of robots
kneath
302
44k
VelocityConf: Rendering Performance Case Studies
addyosmani
326
24k
Designing Experiences People Love
moore
138
23k
Agile that works and the tools we love
rasmusluckow
328
21k
The Invisible Side of Design
smashingmag
298
50k
Building Flexible Design Systems
yeseniaperezcruz
327
38k
Building Applications with DynamoDB
mza
91
6.1k
Music & Morning Musume
bryan
46
6.2k
Rebuilding a faster, lazier Slack
samanthasiow
79
8.7k
We Have a Design System, Now What?
morganepeng
51
7.3k
Transcript
None
None
None
None
None
None
↑/↓ indicates that larger/smaller values were better.
↑/↓ indicates that larger/smaller values were better.
None
None
None
None
• • • • Caltech-UCSD Birds) • ◦ • ◦
• • •
None
None
None
None
None
None
None