A Correspondence Between Normalization Strategies in Artificial and Biological Neural Networks

A fundamental challenge at the interface of machine learning and neuroscience is to uncover computational principles that are shared between artificial and biological neural networks. In deep learning, normalization methods such as batch normalization, weight normalization, and their many variants h...

Descripción completa

Detalles Bibliográficos
Autores principales: Shen, Yang, Wang, Julia, Navlakha, Saket
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MIT Press 2021
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8662716/
https://www.ncbi.nlm.nih.gov/pubmed/34474484
http://dx.doi.org/10.1162/neco_a_01439

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8662716/
https://www.ncbi.nlm.nih.gov/pubmed/34474484
http://dx.doi.org/10.1162/neco_a_01439

Ejemplares similares