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

Authors:
Vijanth S. Asirvadam;Seán F. McLoone;George W. Irwin
Affiliations:
Faculty of Engineering and Computer Technology, Asian Institute of Medicine Science and Technology, 08000 AmanJaya, Sungai Petani, Kedah Darul Aman, Malaysia;Department of Electronic Engineering, National University of Ireland, Maynooth, Maynooth, Co. Kildare, Republic of Ireland;School of Electrical and Electronic Engineering, Queen's University Belfast, Belfast BT9 5AH, N. Ireland, UK
Venue:
Neurocomputing
Year:
2005

Citing 4
Cited 0

A resource-allocating network for function interpolation

Neural Computation
A function estimation approach to sequential learning with neural networks

Neural Computation
A sequential learning scheme for function approximation using minimal radial basis function neural networks

Neural Computation
Fast parallel off-line training of multilayer perceptrons

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

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.