Chargement en cours...

High-dimensional dynamics of generalization error in neural networks

We perform an analysis of the average generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant “high-dimensional” regime where the number of free parameters in the network is on the order of or even larger than the number of examples in the d...

Description complète

Enregistré dans:
Détails bibliographiques
Publié dans:Neural Netw
Auteurs principaux: Advani, Madhu S., Saxe, Andrew M., Sompolinsky, Haim
Format: Artigo
Langue:Inglês
Publié: Pergamon Press 2020
Sujets:
Accès en ligne:https://ncbi.nlm.nih.gov/pmc/articles/PMC7685244/
https://ncbi.nlm.nih.gov/pubmed/33022471
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1016/j.neunet.2020.08.022
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!