Convergence Behavior of DNNs with Mutual-Information-Based Regularization

Information theory concepts are leveraged with the goal of better understanding and improving Deep Neural Networks (DNNs). The information plane of neural networks describes the behavior during training of the mutual information at various depths between input/output and hidden-layer variables. Prev...

Descripción completa

Detalles Bibliográficos
Autores principales: Jónsson, Hlynur, Cherubini, Giovanni, Eleftheriou, Evangelos
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7517266/
https://www.ncbi.nlm.nih.gov/pubmed/33286499
http://dx.doi.org/10.3390/e22070727

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7517266/
https://www.ncbi.nlm.nih.gov/pubmed/33286499
http://dx.doi.org/10.3390/e22070727

Ejemplares similares