The Weights Reset Technique for Deep Neural Networks Implicit Regularization

We present a new regularization method called Weights Reset, which includes periodically resetting a random portion of layer weights during the training process using predefined probability distributions. This technique was applied and tested on several popular classification datasets, Caltech-101,...

Full description

Bibliographic Details

Published in:	Computation
Main Authors:	Grigoriy Plusch, Sergey Arsenyev-Obraztsov, Olga Kochueva
Format:	Article
Language:	English
Published:	MDPI AG 2023-08-01
Subjects:	machine learning deep learning implicit regularization computer vision
Online Access:	https://www.mdpi.com/2079-3197/11/8/148