Accelerating DNN Training Through Selective Localized Learning

Training Deep Neural Networks (DNNs) places immense compute requirements on the underlying hardware platforms, expending large amounts of time and energy. We propose LoCal+SGD, a new algorithmic approach to accelerate DNN training by selectively combining localized or Hebbian learning within a Stoch...

Descripción completa

Detalles Bibliográficos
Autores principales: Krithivasan, Sarada, Sen, Sanchari, Venkataramani, Swagath, Raghunathan, Anand
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8787307/
https://www.ncbi.nlm.nih.gov/pubmed/35087370
http://dx.doi.org/10.3389/fnins.2021.759807

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8787307/
https://www.ncbi.nlm.nih.gov/pubmed/35087370
http://dx.doi.org/10.3389/fnins.2021.759807

Ejemplares similares