A Comparison Between Two Methods to Optimize Cross-Detecting Lines for a Fuzzy Neuron

Abstract

We have described a design algorithm of membership functions for a fuzzy neuron using example-based learning with optimization of cross-detecting lines(Yamakawa et al., 1992). The optimization discussed in (Yamakawa et al., 1992) is called the inefficient cross-detecting line elimination method. We have also described the efficient cross-detecting line selection method as an advanced optimization method(Furukawa et al, 1993). This paper shows a comparison between the inefficient cross-detecting line elimination method and the efficient cross-detecting line selection method, and the typical examples of membership function obtained by both methods. In comparison with the elimination method, the selection method can reduce the number of the common cross-detecting lines (i.e. the number of the sensor arrays) and the CPU time for design of the membership functions of a fuzzy neuron.