Acquisition of fuzzy rules using fuzzy ID3 with ability of learning for AND/OR operators
Isao Hayashi · 2002
An ability of learning for AND/OR operators is discussed to overcome a drawback of fuzzy ID3. In the fuzzy ID3, it is nearly impossible to obtain the most suitable fuzzy rules since the fuzzy ID3 has a couple of problems, i.e., a problem of a lack of representation and an adjusting problem. In our fuzzy ID3, AND/OR operators are formulated using t-norm and t-conorm connectives with parameters and each parameter is adjusted using golden section method. By using golden section method, we get the optimal solution at a high speed. The proposed fuzzy ID3 gives more accurate fuzzy rules by adjusting parameters. If t-conorm connective is selected as AND/OR operator, the decision tree has more flexible representation.