Analysis of Deep Convolutional Neural Networks Using Tensor Kernels and Matrix-Based Entropy

Analyzing deep neural networks (DNNs) via information plane (IP) theory has gained tremendous attention recently to gain insight into, among others, DNNs’ generalization ability. However, it is by no means obvious how to estimate the mutual information (MI) between each hidden layer and the input/de...

Descripción completa

Detalles Bibliográficos
Autores principales: Wickstrøm, Kristoffer K., Løkse, Sigurd, Kampffmeyer, Michael C., Yu, Shujian, Príncipe, José C., Jenssen, Robert
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10297039/
https://www.ncbi.nlm.nih.gov/pubmed/37372243
http://dx.doi.org/10.3390/e25060899

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10297039/
https://www.ncbi.nlm.nih.gov/pubmed/37372243
http://dx.doi.org/10.3390/e25060899

Ejemplares similares