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...

Descripción completa

Detalles Bibliográficos
Autores principales: Advani, Madhu S., Saxe, Andrew M., Sompolinsky, Haim
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Pergamon Press 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7685244/
https://www.ncbi.nlm.nih.gov/pubmed/33022471
http://dx.doi.org/10.1016/j.neunet.2020.08.022

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7685244/
https://www.ncbi.nlm.nih.gov/pubmed/33022471
http://dx.doi.org/10.1016/j.neunet.2020.08.022

Ejemplares similares