Training multilayer perceptron classifiers based on a modifiedsupport vector method
Suykens, J.A.K.
Vandewalle, J.
Dept. of Electr. Eng., Katholieke Univ., Leuven ;
This paper appears in: Neural Networks, IEEE Transactions on
Publication Date: Jul 1999
Volume: 10,
Issue: 4
On page(s): 907-911
ISSN: 1045-9227
References Cited: 16
CODEN: ITNNEP
INSPEC Accession Number: 6312130
DOI: 10.1109/72.774254
Posted online: 2002-08-06 22:33:08.0
Abstract
In this paper we describe a training method for one hidden layer
multilayer perceptron classifier which is based on the idea of support
vector machines (SVM). An upper bound on the Vapnik-Chervonenkis (VC)
dimension is iteratively minimized over the interconnection matrix of
the hidden layer and its bias vector. The output weights are determined
according to the support vector method, but without making use of the
classifier form which is related to Mercer's condition. The method is
illustrated on a two-spiral classification problem
Index Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
