TITLE: Neural Classifier Construction Using Regularization, Pruning and Test Error Estimation

AUTHOR: Mads Hintz-Madsen, Lars Kai Hansen, Jan Larsen, Morten With Pedersen, and Michael Larsen
connect, Department of Mathematical Modelling, Building 321
Technical University of Denmark, DK-2800 Lyngby, Denmark
emails: mhm,lkhansen,jl@imm.dtu.dk
www: http://eivind.imm.dtu.dk


In this paper we propose a method for construction of feed-forward neural classifiers based on regularization and adaptive architectures. Using a penalized maximum likelihood scheme, we derive a modified form of the entropic error measure and an algebraic estimate of the test error. In conjunction with Optimal Brain Damage pruning, a test error estimate is used to select the network architecture. The scheme is evaluated on four classification problems.

To appear in Neural Networks, 1998.