33
/fr/
AIzaSyB4mHJ5NPEv-XzF7P6NDYXjlkCWaeKw5bc
November 30, 2025
3276542
291921
1
Create a timeline
Public Timelines
For education
For educational institutions
For teachers
For students
Cabinet
For educational institutions
For teachers
For students
Open cabinet
FAQ
Close
Create a timeline
Public timelines
FAQ
About & Feedback
Un accord
Confidentialité
FAQ
Support 24/7
Cabinet
Get premium
Donate
10 janv. 2014 - Jimmy Ba: Do Deep Nets Really eed to be Deep? , NIPS, 2014
Description:
本文通过实验证明,浅前馈网络可以学习深网以前学习到的复杂函数,达到以前只有深网模型才能达到的精度。此外,在某些情况下,浅网可以使用与原始深网模型相同数量的参数来学习这些深网函数。
Ajouté au bande de temps:
knowledge transfer/ distillation
By
龚成
30 août 2019
0
0
552
Date:
10 janv. 2014
Maintenaint
~ Il y a 11 ans
About & Feedback
Un accord
Confidentialité
FAQ
Support 24/7
Cabinet
Get premium
Donate
The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.
Secured with SSL