A FLEXIBLE NEUROFUZZY CELL STRUCTURE FOR GENERAL FUZZY INFERENCE

This paper presents and investigates a neural network structure which can perform general fuzzy inference. This system consists of a number of parallel neural network units which are called ''flexible inference cells'' (FICs). Each FIC implements a single-input/single-output (SIS O) IF-THEN rule of a fuzzy knowledge base. The assumption of SISO fuzz y rules allows the implementation of any complex fuzzy inference algor ithm (for control or other decision making purposes), since any MIMO ( multi-input/multi-output) rule can be decomposed into an equivalent se t of MISO (multi-input/single-output) rules, and a MISO rule can be de composed to a set of SISO rules. The paper discusses the assumptions a nd requirements for the proposed neurofuzzy structure, and classifies the FICs into four categories. Some results derived by simulation usin g 3125 exemplar patterns produced computationally are provided.