eCite Digital Repository

Are binary synapses superior to graded weight representations in stochastic attractor networks?

Citation

Satel, J and Trappenberg, T and Fine, A, Are binary synapses superior to graded weight representations in stochastic attractor networks?, Cognitive neurodynamics, 3, (3) pp. 243-250. ISSN 1871-4080 (2009) [Refereed Article]

Copyright Statement

Copyright 2009 Springer Science+Business Media B.V.

DOI: doi:10.1007/s11571-009-9083-3

Abstract

Synaptic plasticity is an underlying mechanism of learning and memory in neural systems, but it is controversial whether synaptic efficacy is modulated in a graded or binary manner. It has been argued that binary synaptic weights would be less susceptible to noise than graded weights, which has impelled some theoretical neuroscientists to shift from the use of graded to binary weights in their models. We compare retrieval performance of models using both binary and graded weight representations through numerical simulations of stochastic attractor networks. We also investigate stochastic attractor models using multiple discrete levels of weight states, and then investigate the optimal threshold for dilution of binary weight representations. Our results show that a binary weight representation is not less susceptible to noise than a graded weight representation in stochastic attractor models, and we find that the load capacities with an increasing number of weight states rapidly reach the load capacity with graded weights. The optimal threshold for dilution of binary weight representations under stochastic conditions occurs when approximately 50% of the smallest weights are set to zero.

Item Details

Item Type:Refereed Article
Keywords:attention
Research Division:Psychology and Cognitive Sciences
Research Group:Cognitive Sciences
Research Field:Computer Perception, Memory and Attention
Objective Division:Expanding Knowledge
Objective Group:Expanding Knowledge
Objective Field:Expanding Knowledge in Psychology and Cognitive Sciences
Author:Satel, J (Dr Jason Satel)
ID Code:111158
Year Published:2009
Web of Science® Times Cited:5
Deposited By:Psychology
Deposited On:2016-09-01
Last Modified:2016-11-15
Downloads:0

Repository Staff Only: item control page