A neural network model with bounded-weights for pattern classification

A neural network model with bounded-weights for pattern classification

0.00 Avg rating0 Votes
Article ID: iaor2005723
Country: United Kingdom
Volume: 31
Issue: 9
Start Page Number: 1411
End Page Number: 1426
Publication Date: Aug 2004
Journal: Computers and Operations Research
Authors: , ,
Abstract:

A new neural network model is proposed based on the concepts of multi-layer perceptrons, radial basis functions, and support vector machines (SVM). This neural network model is trained using the least squared error as the optimization criterion, with the magnitudes of the weights on the links being limited to a certain range. Like the SVM model, the weight specification problem is formulated as a convex quadratic programming problem. However, unlike the SVM model, it does not require that kernel functions satisfy Mercer's condition, and it can readily extended to multi-class classification. Some experimental results are reported.

Reviews

Required fields are marked *. Your email address will not be published.