Sparse distributed memory using N-of-M codes

Furber, SB

doi:10.1016/j.neunet.2004.07.003

Sparse distributed memory using N-of-M codes

2004-12-01

32

PRE

AI

DOI：10.1016/j.neunet.2004.07.003

Original

Original request for help

Save

Abstract

En 中文

An analysis is presented of a sparse distributed memory (SDM) inspired by that described by Kanerva [Kanerva, P. (1988). Sparse distributed memory. Cambridge, MA: MIT Press] but modified to facilitate an implementation based on spiking neurons. The memory presented here employs sparse binary N-of-M codes, unipolar binary synaptic weights and a simple Hebbian learning rule. It is a two-layer network. the first (fixed) layer being similar to the `address decoder' in Jaeckel's [Jaeckel, L.A. (1989). A class of designs for a sparse distributed memory. RIACS Technical Report 89.30, NASA Ames Research Centre] `hyperplane' variant of Kanerva's SDM and the second (writeable) 'data store' layer being a correlation matrix memory as first proposed by Willshaw et al. [Willshaw, D. J., Buneman, O.P., & Longuet-Higgins, H.C. (1969). Non-holographic associative memory. Nature, 222, 960-962]. The resulting network is shown to have good storage efficiency and is scalable. The analysis is supported by numerical simulations and gives results that enable the configuration of the memory to be optinused for a range of noiseless and noisy environments. (C) 2004 Elsevier Ltd. All rights reserved.

Keywords:

neural networks

spiking neurons

sparse distributed memory

associative memory

correlation matrix memory

unipolar weights

N-of-M codes

Sparse distributed memory using N-of-M codes

Abstract

AI Summary

Journal

Organization