A novel neural algorithm and its application in solving fuzzy relation equations

We propose a novel algorithm for solving various types of fuzzy relation equations. The algorithm is based an a special designed fuzzy neuron. This fuzzy neuron is founded by replacing some operators of the traditional neuron with a pair of abstract fuzzy operators which we call fuzzy neuron operators. We also discuss the relationship between the fuzzy neuron operators and t-norm/t-conorm, and point out that fuzzy neuron operators are based on t-norm but much wider than t-norm. Finally, we report some simulation results with some typical compositional operators.