Neural Network Structure Optimization by Simulated Annealing

A critical problem in large neural networks is over parameterization with a large number of weight parameters, which limits their use on edge devices due to prohibitive computational power and memory/storage requirements. To make neural networks more practical on edge devices and real-time industria...

Descripción completa

Detalles Bibliográficos
Autores principales: Kuo, Chun Lin, Kuruoglu, Ercan Engin, Chan, Wai Kin Victor
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947290/
https://www.ncbi.nlm.nih.gov/pubmed/35327859
http://dx.doi.org/10.3390/e24030348

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947290/
https://www.ncbi.nlm.nih.gov/pubmed/35327859
http://dx.doi.org/10.3390/e24030348

Ejemplares similares