Main Menu (Mobile)- Block

Main Menu - Block

A network of spiking neurons for computing sparse representations in an energy-efficient way.

Our Research / Publications
janelia7_blocks-janelia7_biblio_header | block
Neural computation. 2012 Nov;24:2852-72. doi: 10.1162/NECO_a_00353
View Article on
A network of spiking neurons for computing sparse representations in an energy-efficient way.
Hu T, Genkin A, Chklovskii DB
janelia7_blocks-janelia7_biblio_abstract | block

Abstract

Computing sparse redundant representations is an important problem in both applied mathematics and neuroscience. In many applications, this problem must be solved in an energy-efficient way. Here, we propose a hybrid distributed algorithm (HDA), which solves this problem on a network of simple nodes communicating by low-bandwidth channels. HDA nodes perform both gradient-descent-like steps on analog internal variables and coordinate-descent-like steps via quantized external variables communicated to each other. Interestingly, the operation is equivalent to a network of integrate-and-fire neurons, suggesting that HDA may serve as a model of neural computation. We show that the numerical performance of HDA is on par with existing algorithms. In the asymptotic regime, the representation error of HDA decays with time, t, as 1/t. HDA is stable against time-varying noise; specifically, the representation error decays as 1/√t for gaussian white noise.

PMID: 22920853 [PubMed - indexed for MEDLINE]

node:body | entity_field
janelia7_blocks-janelia7_biblio_authors | block

Janelia Authors

janelia7_blocks-janelia7_biblio_tools | block