A hybrid linear/nonlinear training algorithm for feedforward neural networks

Abstract

This paper presents a new hybrid optimization strategy for training feedforward neural networks. The algorithm combines gradient-based optimization of nonlinear weights with singular value decomposition (SVD) computation of linear weights in one integrated routine. It is described for the multilayer perceptron (MLP) and radial basis function (RBF) networks and then extended to the local model network (LMN), a new feedforward structure in which a global nonlinear model is constructed from a set of locally valid submodels. Simulation results are presented demonstrating the superiority of the new hybrid training scheme compared to second-order gradient methods. It is particularly effective for the LMN architecture where the linear to nonlinear parameter ratio is large.

DOI: 10.1109/72.701180

15 Figures and Tables

Statistics

0102030'00'02'04'06'08'10'12'14'16
Citations per Year

193 Citations

Semantic Scholar estimates that this publication has 193 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{McLoone1998AHL, title={A hybrid linear/nonlinear training algorithm for feedforward neural networks}, author={Se{\'a}n F. McLoone and M. D. Brown and George W. Irwin and Gordon Lightbody}, journal={IEEE transactions on neural networks}, year={1998}, volume={9 4}, pages={669-84} }