Optimization in fuzzy flip-flop neural networks

Abstract

The fuzzy J-K and D flip-flops present s-shape transfer characteristics in same particular cases. We propose the fuzzy flip-flop neurons; single input-single output units derived from fuzzy flip-flops as sigmoid function generators. The fuzzy neurons-based neural networks, Fuzzy Flip-Flop Neural Networks (FNN) parameters are quasi optimized using a second-order gradient algorithm, the Levenberg-Marquardt method (LM) and an evolutionary algorithm, the Bacterial Memetic Algorithm with Modified Operator Execution Order (BMAM). The quasi optimized FNN's performance based on Dombi and Yager fuzzy operations has been examined with a series of test functions. © 2010 Springer-Verlag Berlin Heidelberg.