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/2134/5795

Title: A normalized gradient algorithm for an adaptive recurrent perceptron
Authors: Chambers, Jonathon
Sherliker, Warren
Mandic, Danilo P.
Issue Date: 2000
Publisher: © IEEE
Citation: CHAMBERS, J.A., SHERLIKER, W. and MANDIC, D.P., 2000. A normalized gradient algorithm for an adaptive recurrent perceptron. IN: IEEE International Conference on Acoustics, Speech, and Signal Processing, (ICASSP '00), Istanbul, 5-9 June, Vol. 1, pp. 396-399
Abstract: A normalized algorithm for on-line adaptation of a recurrent perceptron is derived. The algorithm builds upon the normalized backpropagation (NBP) algorithm for feedforward neural networks, and provides an adaptive learning rate and normalization for a recurrent perceptron learning algorithm. The algorithm is based upon local linearization about the current point in the state-space of the network. Such a learning rate is normalized by the squared norm of the gradient at the neuron, which extends the notion of normalized linear algorithms to the nonlinear case
Description: This is a conference paper [© IEEE]. It 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/ICASSP.2000.861988
URI: https://dspace.lboro.ac.uk/2134/5795
ISBN: 0780362934
Appears in Collections:Conference Papers and Presentations (Mechanical, Electrical and Manufacturing Engineering)

Files associated with this item:

File Description SizeFormat
chambers.pdf349.81 kBAdobe PDFView/Open


SFX Query

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