Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Network 1 (1990) 105-122. Printed in the UK Learning in neural network memories

Summary: Network 1 (1990) 105-122. Printed in the UK
Learning in neural network memories
L F Abbott
Physics Department, Brandeis University, Waltham, MA 02254, USA
Received 19 September 1989
Abstract. Various algorithms for constructing a synaptic coupling matrix which can as-
sociatively map input patterns onto nearby stored memory patterns are reviewed. Issues
discussed include performance, capacity, speed, efficiency and biological plausibility.
1. Introduction
The term `learning' is applied to a wide range of activities associated with the construc-
tion of neural networks ranging from single-layer binary classifiers [l] to multilayered
systems performing relatively sophisticated tasks [2].Any reviewer hoping to cover this
field in a reasonable amount of time and space must do so with a severely restricted
viewpoint. Here, I will concentrate on a fairly simple task, associative memory, ac-
complished by a single-layered iterative network of binary elements [3-51. This area is
considered because there are now available a large number of precise analytic results
and a wealth of ideas and approaches have appeared and been analysed in detail.
Most neural network modelling relies crucially on the assumption that synaptic
plasticity [6] is a (or perhaps the) key component in the remarkable adaptive behaviour


Source: Abbott, Laurence - Center for Neurobiology and Behavior & Department of Physiology and Cellular Biophysics, Columbia University


Collections: Biology and Medicine