K. Cherkauer & J. Shavlik (1995).
Rapidly Estimating the Quality of Input Representations for Neural Networks. Working Notes of the IJCAI-95 Workshop on Data Engineering for Inductive Learning, Fourteenth International Joint Conference on Artificial Intelligence, Montreal, Quebec, Canada.

This publication is available in PDF and available in postscript.

Abstract:

The choice of an input representation for machine learning can have a profound impact on the accuracy of the learned model in classifying novel instances. A reliable method of rapidly estimating the value of a representation, independent of the learner, would be a powerful tool in the search for better representations. We introduce a fast representation- quality measure that is more accurate than Rendell and Ragavan's blurring metric in rank ordering input representations for neural networks on two difficult, real-world datasets. This work constitutes a step forward both in representation quality measures and in our understanding of the characteristics that engender good representations.

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