Relations between the a priori and a posteriori errors in nonlinear adaptive neural filters

Mandic, D. P. and Chambers, J. A. (1999) Relations between the a priori and a posteriori errors in nonlinear adaptive neural filters. Neural Computation, 12 (6). pp. 1285-1292. ISSN 0899-7667

Full text not available from this repository.

Abstract

The lower bounds for the a posteriori prediction error of a nonlinear predictor realized as a neural network are provided. These are obtained for a priori adaptation and a posteriori error networks with sigmoid nonlinearities trained by gradient-descent learning algorithms. A contractivity condition is imposed on a nonlinear activation function of a neuron so that the a posteriori prediction error is smaller in magnitude than the corresponding a priori one. Furthermore, an upper bound is imposed on the learning rate ? so that the approach is feasible. The analysis is undertaken for both feedforward and recurrent nonlinear predictors realized as neural networks.

Item Type: Article
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Vishal Gautam
Date Deposited: 10 Mar 2011 09:44
Last Modified: 21 Apr 2020 21:22
URI: https://ueaeprints.uea.ac.uk/id/eprint/23719
DOI: 10.1162/089976600300015358

Actions (login required)

View Item View Item