Fuzzy Flip-Flop Based Neural Network as a Function Approximator

Artificial neural networks and fuzzy logic systems, in the context of approximate reasoning, share common features and techniques. A family of fuzzy flip-flops is proposed, based on an artificial neural network-like structure which is suitable for approximating many-input one-output nonlinear functions. The neurons in the multilayer perceptron networks typically employ sigmoidal activation functions. The next state of the fuzzy J-K flip-flops (F3) using Yager and Dombi operators present quasi-S-shaped characteristics. The paper proposes the investigation of the possibility of constructing multilayer perceptrons from such fuzzy units. Each of the two candidates for F3-based neurons is examined for its training capability by evaluating and comparing the approximation properties in the context of different transcendental functions with one-input and multi-input cases. Simulation results are presented.