Abstract

A neural network construction method for problems specified for data sets with in- and/or output values in the continuous or discrete domain is described and evaluated. This approach is based on a Boolean approximation of the data set and is generic for various neural network architectures. The construction method takes advantage of a construction method for Boolean problems without increasing the dimensions of the in- or output vectors, which is a strong advantage over approaches which work on a binarized version of the data set with an increased number of in- and output elements. Further, the networks are pruned in a second phase in order to obtain very small networks.

Details

Actions