ROUGH KNOWLEDGE-BASED NETWORK, FUZZINESS AND CLASSIFICATION

A method of integrating rough sets and fuzzy multilayer perceptron (ML P) for designing a knowledge-based network for pattern recognition pro blems is described. Rough set theory is used to extract crude knowledg e from the input domain in the form of rules. The syntax of these rule s automatically determines the optimal number of hidden nodes while th e dependency factors are used in the initial weight encoding. Results on classification of speech data demonstrate the superiority of the sy stem over the fuzzy and conventional versions of the MLP.