Complexity control by gradient descent in deep networks

Understanding the underlying mechanisms behind the successes of deep networks remains a challenge. Here, the author demonstrates an implicit regularization in training deep networks, showing that the control of complexity in the training is hidden within the optimization technique of gradient descen...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tomaso Poggio, Qianli Liao, Andrzej Banburski
Format: article
Langue:EN
Publié: Nature Portfolio 2020
Sujets:
Q
Accès en ligne:https://doaj.org/article/a50e459c37be4efd87800b05dd1d5ce3
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!