Create a timeline

Public timelines

10 gen 2014 anni - Jimmy Ba: Do Deep Nets Really eed to be Deep? , NIPS, 2014

Descrizione:

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。

Aggiunto al nastro di tempo:

knowledge transfer/ distillation

30 ago 2019

0

0

499

Data:

10 gen 2014 anni

Adesso

~ 11 years ago

About & Feedback Accordo Privatezza Biblioteca FAQ

Cabinet Get premium

Donate

The service accepts bank transfer (ACH, Wire) or cards (Visa, MasterCard, etc). Processed by Stripe.

Secured with SSL