Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/5798

Title: Toward an optimal PRNN-based nonlinear predictor
Authors: Mandic, Danilo P.
Chambers, Jonathon
Keywords: Forgetting factor
Nesting
Nonlinear prediction
PRNN
RNN
Issue Date: 1999
Publisher: © IEEE
Citation: MANDIC, D.P. and CHAMBERS, J.A., 1999. Toward an optimal PRNN-based nonlinear predictor. IEEE Transactions on Neural Networks, 10(6), pp. 1435-1442
Abstract: We present an approach for selecting optimal parameters for the pipelined recurrent neural network (PRNN) in the paradigm of nonlinear and nonstationary signal prediction. We consider the role of nesting, which is inherent to the PRNN architecture. The corresponding number of nested modules needed for a certain prediction task, and their contribution toward the final prediction gain give a thorough insight into the way the PRNN performs, and offers solutions for optimization of its parameters. In particular, nesting allows the forgetting factor in the cost function of the PRNN to exceed unity, hence it becomes an emphasis factor. This compensates for the small contribution of the distant modules to the prediction process, due to nesting, and helps to circumvent the problem of vanishing gradient, experienced in RNNs for prediction. The PRNN is shown to outperform the linear least mean square and recursive least squares predictors, as well as previously proposed PRNN schemes, at no expense of additional computational complexity
Description: This article was published in the journal IEEE Transactions on Neural Networks [© IEEE] and is also available at: http://ieeexplore.ieee.org/. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Version: Published
DOI: 10.1109/72.809088
URI: https://dspace.lboro.ac.uk/2134/5798
ISSN: 1045-9227
Appears in Collections:Published Articles (Electronic, Electrical and Systems Engineering)

Files associated with this item:

File Description SizeFormat
mandic4.pdf196.75 kBAdobe PDFView/Open

 

SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.