University of Surrey

Test tubes in the lab Research in the ATI Dance Research

A posteriori real-time recurrent learning schemes for a recurrent neural network based nonlinear predictor

Mandic, DP and Chambers, JA (1998) A posteriori real-time recurrent learning schemes for a recurrent neural network based nonlinear predictor IEE Proceedings: Vision, Image and Signal Processing, 145 (6). pp. 365-370.

Full text not available from this repository.

Abstract

Recurrent neural networks (RNNs) are well established for the nonlinear and nonstationary signal prediction paradigm. Appropriate learning algorithms, such as the real-time recurrent learning (RTRL) algorithm, have been developed for that purpose. However, little is known about the RNN time-management policy. Here, insight is provided into the time management of the RNN, and an a posteriori approach to the RNN based nonlinear signal prediction paradigm is offered. Based upon the chosen time-management policy, algorithms are developed, from the a priori learning-a priori error strategy through to the a posteriori learning-a posteriori error strategy. Compared with the a priori algorithms, the a posteriori algorithms offered are shown to provide a better prediction performance with little further expense in terms of computational complexity. Simulations undertaken on speech using the newly introduced algorithms confirm the theoretical results.

Item Type: Article
Authors :
NameEmailORCID
Mandic, DPUNSPECIFIEDUNSPECIFIED
Chambers, JAj.a.chambers@surrey.ac.ukUNSPECIFIED
Date : 1 December 1998
Identification Number : https://doi.org/10.1049/ip-vis:19982458
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:27
Last Modified : 17 May 2017 13:27
URI: http://epubs.surrey.ac.uk/id/eprint/839283

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800