Combining lateral and elastic interactions: topology-preserving elastic nets

Tereshko, Valery and Allinson, Nigel M. (2002) Combining lateral and elastic interactions: topology-preserving elastic nets. Neural Processing Letters, 15 (3). pp. 213-223. ISSN 1370-4621

Full content URL: http://dx.doi.org/10.1023/A:1015721115089

Full text not available from this repository.

Item Type:Article
Item Status:Live Archive

Abstract

We have developed a topology-preserving elastic net which combines both lateral and synaptic interactions to obtain topologically ordered representations (receptive fields) of an external stimulus. Existing neural models that preserve the topology by utilizing lateral interactions, such as the Kohonen-type maps, and by utilizing synaptic interactions, such as elastic-type nets, appear as limiting cases of this model. Utilizing both lateral and synaptic interactions can be beneficial for preservation of the topology.

Keywords:Algorithms, Annealing, Free energy, Learning systems, Optimization, Statistical mechanics, Elastic nets, Neural networks
Subjects:G Mathematical and Computer Sciences > G730 Neural Computing
Divisions:College of Science > School of Computer Science
ID Code:8571
Deposited On:17 Apr 2013 20:31

Repository Staff Only: item control page