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

V.S. Asirvadam, Seán McLoone, George Irwin

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Computionally 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. (c) 2005 Elsevier B.V. All rights reserved.
Original languageEnglish
Pages (from-to)142-157
Number of pages16
JournalNeurocomputing
Volume69
Issue number1-3
DOIs
Publication statusPublished - Dec 2005

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cellular and Molecular Neuroscience

Fingerprint

Dive into the research topics of 'Computationally efficient sequential learning algorithms for direct link resource-allocating networks'. Together they form a unique fingerprint.

Cite this