Interpretation preservation of adaptive fuzzy inference systems

AbstractThe membership functions of an adaptive fuzzy inference system, during the adaptation process, may lose the meaning which was initially assigned to them. In this paper, the concept of rough sets is used to propose a constraint training algorithm. The proposed algorithm maintains the interpretation of the adaptive fuzzy inference systems during the training. The constraints on membership functions are implemented by means of hard or soft limit bounds on the updating parameters of membership functions. An example to illustrate the algorithm is included