Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/16537
Title: Selection of weight quantisation accuracy for radial basis function neural network using stochastic sensitivity measure
Authors: Ng, WWY
Yeung, DS
Issue Date: 2003
Publisher: Institution of Engineering and Technology
Source: Electronics letters, 2003, v. 39, no. 10, p. 787-789 How to cite?
Journal: Electronics letters 
Abstract: Minimising the number of bits per connection weight in hardware realisation of a radial basis function neural network (RBFNN) will result in high-speed and low-cost implementation, with possible increase in output error. A weight quantisation accuracy selection method is proposed, to find an appropriate number of bits for a given stochastic sensitivity measure, which quantifies the relationship between the variance of the output error and first- and second-order statistics of input, weight and their perturbations.
URI: http://hdl.handle.net/10397/16537
ISSN: 0013-5194
EISSN: 1350-911X
DOI: 10.1049/el:20030499
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

20
Last Week
0
Last month
1
Citations as of Dec 9, 2017

WEB OF SCIENCETM
Citations

7
Last Week
0
Last month
0
Citations as of Dec 9, 2017

Page view(s)

49
Last Week
1
Last month
Checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric



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