Memory-Efficient Deep Learning on a SpiNNaker 2 Prototype

The memory requirement of deep learning algorithms is considered incompatible with the memory restriction of energy-efficient hardware. A low memory footprint can be achieved by pruning obsolete connections or reducing the precision of connection strengths after the network has been trained. Yet, th...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Publicado no:Front Neurosci
Main Authors: Liu, Chen, Bellec, Guillaume, Vogginger, Bernhard, Kappel, David, Partzsch, Johannes, Neumärker, Felix, Höppner, Sebastian, Maass, Wolfgang, Furber, Steve B., Legenstein, Robert, Mayr, Christian G.
Formato: Artigo
Idioma:Inglês
Publicado em: Frontiers Media S.A. 2018
Assuntos:
Neuroscience
Acesso em linha:https://ncbi.nlm.nih.gov/pmc/articles/PMC6250847/
https://ncbi.nlm.nih.gov/pubmed/30505263
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3389/fnins.2018.00840
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!

Registos relacionados