Neural net approximations to solutions of systems of fuzzy linear equations
James J. Buckley, Yoichi Hayashi · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
This paper continues previous research (Buckley and Eslami, 1995, Buckley and Hayashi, 1995, Hayashi and Buckley,1996) into using neural nets to solve fuzzy problems. We show how to train neural nets, with certain sign constraints on their weights, using genetic algorithms, to approximate solutions to systems of fuzzy linear equations. This paper presents a new application of layered, feedforward, neural nets with sign restrictions on their weights.