Carregant...

Mutual Information Based Learning Rate Decay for Stochastic Gradient Descent Training of Deep Neural Networks

This paper demonstrates a novel approach to training deep neural networks using a Mutual Information (MI)-driven, decaying Learning Rate (LR), Stochastic Gradient Descent (SGD) algorithm. MI between the output of the neural network and true outcomes is used to adaptively set the LR for the network,...

Descripció completa

Guardat en:
Dades bibliogràfiques
Publicat a:Entropy (Basel)
Autor principal: Vasudevan, Shrihari
Format: Artigo
Idioma:Inglês
Publicat: MDPI 2020
Matèries:
Accés en línia:https://ncbi.nlm.nih.gov/pmc/articles/PMC7517082/
https://ncbi.nlm.nih.gov/pubmed/33286332
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3390/e22050560
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!