Title :
A Boolean approach to construct neural networks for non-Boolean problems
Author :
Thimm, Georg ; Fiesler, Emile
Author_Institution :
IDIAP, Martigny, Switzerland
Abstract :
A neural network construction method for problems specified for data sets with input 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 input or output vectors, which is an advantage over approaches which work on a binarized version of the data set with an increased number of input and output elements. Further, the networks are pruned in a second phase in order to obtain very small networks.
Keywords :
Boolean functions; network topology; neural net architecture; Boolean approach; continuous domain; data sets; discrete domain; input values; input vectors; network pruning; neural network architectures; neural network construction method; nonBoolean problems; output values; output vectors; vector dimensions; Logic; Network topology; Neural networks; Polynomials;
Conference_Titel :
Tools with Artificial Intelligence, 1996., Proceedings Eighth IEEE International Conference on
Print_ISBN :
0-8186-7686-7
DOI :
10.1109/TAI.1996.560784
