Variable binding by synaptic strength change

Huyck, Christian R. (2009) Variable binding by synaptic strength change. Connection Science, 21 (4). pp. 327-357. ISSN 0954-0091

[img]
Preview
PDF
584kB

Official URL: http://dx.doi.org/10.1080/09540090902954188

This item is available in the Library Catalogue

Abstract

Variable binding is a difficult problem for neural networks. Two new mechanisms for binding by synaptic change are presented, and in both, bindings are erased and can be reused. The first is based on the commonly used learning mechanism of permanent change of synaptic weight, and the second on synaptic change which decays. Both are biologically motivated models. Simulations of binding on a paired association task are shown with the first mechanism succeeding with a 97.5% F-Score, and the second performing perfectly. Further simulations show that binding by decaying synaptic change copes with cross talk, and can be used for compositional semantics. It can be inferred that binding by permanent change accounts for these, but it faces the stability plasticity dilemma. Two other existing binding mechanism, synchrony and active links, are compatible with these new mechanisms. All four mechanisms are compared and integrated in a Cell Assembly theory.

Item Type:Article
Research Areas:School of Science and Technology > Computer and Communications Engineering
ID Code:4301
Useful Links:
Deposited On:02 Mar 2010 14:29
Last Modified:20 Jul 2014 01:02

Repository staff only: item control page

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year