Logo

Computationally efficient sequential learning algorithms for direct link resource-allocating networks

Asirvadam , Vijanth Sagayan and McLoone, Sean and Irwin, George W (2005) Computationally efficient sequential learning algorithms for direct link resource-allocating networks. Neurocomputing, 69 (1-3). pp. 142-157. ISSN 0925-2312

Full text not available from this repository.

Official URL: http://www.elsevier.com/wps/find/journaldescriptio...

Abstract

Computationally efficient sequential learning algorithms are developed for direct-link resource-allocating networks (DRANs). These are achieved by decomposing existing recursive training algorithms on a layer by layer and neuron by neuron basis. This allows network weights to be updated in an efficient parallel manner and facilitates the implementation of minimal update extensions that yield a significant reduction in computation load per iteration compared to existing sequential learning methods employed in resource-allocation network (RAN) and minimal RAN (MRAN) approaches. The new algorithms, which also incorporate a pruning strategy to control network growth, are evaluated on three different system identification benchmark problems and shown to outperform existing methods both in terms of training error convergence and computational efficiency.

Item Type:Article
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments / MOR / COE:Departments > Electrical & Electronic Engineering
ID Code:3826
Deposited By: Dr Vijanth Sagayan Asirvadam
Deposited On:04 Jan 2011 00:41
Last Modified:04 Jan 2011 00:41

Repository Staff Only: item control page