ProAct: Progressive Training for Hybrid Clipped Activation Function to Enhance Resilience of DNNs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mousavi, Seyedhamidreza, Ahmadilivani, Mohammad Hasan, Raik, Jaan, Jenihhin, Maksim, Daneshtalab, Masoud
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2406.06313