Title
Radial basis function networks and complexity regularization in function learning.
Abstract
In this paper we apply the method of complexity regularization to derive estimation bounds for nonlinear function estimation using a single hidden layer radial basis function network. Our approach differs from previous complexity regularization neural-network function learning schemes in that we operate with random covering numbers and l(1) metric entropy, making it possible to consider much broader families of activation functions, namely functions of bounded variation. Some constraints previously imposed on the network parameters are also eliminated this way. The network is trained by means of complexity regularization involving empirical risk minimization. Bounds on the expected risk in terms of the sample size are obtained for a large class of loss functions. Rates of convergence to the optimal loss are also derived.
Year
DOI
Venue
1996
10.1109/72.661120
IEEE Transactions on Neural Networks
Keywords
DocType
Volume
empirical risk minimization,nonlinear function estimation,expected risk,radial basis function network,loss function,previous complexity regularization neural-network,complexity regularization,activation function,network parameter,basis function network,estimation bound,function learning
Conference
9
Issue
ISSN
Citations 
2
1045-9227
24
PageRank 
References 
Authors
1.83
12
2
Name
Order
Citations
PageRank
A. Krzyzak158563.11
Linder, Tamás2241.83