Should Under-parameterized Student Networks Copy or Average Teacher Weights?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Şimşek, Berfin, Bendjeddou, Amire, Gerstner, Wulfram, Brea, Johanni
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Neural and Evolutionary Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2311.01644