Evolutionary strategy for learning multiple-valued logic functions

被引:0
|
作者
Ngom, A [1 ]
Simovici, DA [1 ]
Stojmenovic, I [1 ]
机构
[1] Univ Windsor, Dept Comp Sci, Windsor, ON N9B 3P4, Canada
关键词
multiple-valued logic; multiple-threshold perceptron; evolution strategy; neural network; partitioning method; constructive algorithm;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V subset of or equal to K-n 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 cot-responding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.
引用
收藏
页码:731 / 737
页数:7
相关论文
共 50 条