K. Cherkauer & J. Shavlik (1996).
Rapid Quality Estimation of Neural Network Input Representations. Advances in Neural Information Processing Systems, pp. 45-51, Denver, CO. MIT Press.

This publication is available in PDF and available in postscript.

Abstract:

The choice of an input representation for a neural network can have a profound impact on its accuracy in classifying novel instances. However, neural networks are typically computationally expensive to train, making it difficult to test large numbers of alternative representations. This paper introduces fast quality measures for neural network representations, allowing one to quickly and accurately estimate which of a collection of possible representations for a problem is the best. We show that our measures for ranking representations are more accurate than a previously published measure, based on experiments with three difficult, real-world pattern recognition problems.

Return to the publications of the Univ. of Wisconsin Machine Learning Research Group.