Evolutionary Strategy for Learning Multiple-Valued Logic Functions
Alioune Ngom, Dan A. Simovici, and Ivan Stojmenovic
We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V Kn is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.