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,...

Descripció completa

Dades bibliogràfiques

Autors principals:	Grigoriy Plusch, Sergey Arsenyev-Obraztsov, Olga Kochueva
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2023-08-01
Col·lecció:	Computation
Matèries:	machine learning deep learning implicit regularization computer vision
Accés en línia:	https://www.mdpi.com/2079-3197/11/8/148
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!