TITLE: Early Stop Criterion from the Bootstrap Ensemble
AUTHORS: Lars Kai Hansen, Jan Larsen, Torben Fog
         CONNECT, Department of Mathematical Modelling, Build. 321
         Technical University of Denmark
         DK-2800 Lyngby, Denmark
         emails: lkhansen,jl,tf@imm.dtu.dk


ABSTRACT:
This paper addresses the problem of generalization error estimation in neural networks. A new early stop criterion based on a Bootstrap estimate of the generalization error is suggested. The estimate does
not require the network to be trained to the minimum of the cost function, as required by other methods based on asymptotic theory. Moreover, in contrast to methods based on cross-validation which require data left out for testing, and thus biasing the estimate, the Bootstrap technique does not have this disadvantage. The potential of the suggested technique is demonstrated on various time-series problems.

This research is supported by the Danish Natural Science
and Technical Research Councils through the Danish Computational
Neural Network Center.
JL furthermore acknowledge the
Radio Parts Foundation for financial support.


In proceedings of ICASSP-97, Munich, Germany, April, 1997.