Utilizing a new feed-back fuzzy neural network for solving a system of fuzzy equations

This paper intends to oer a new iterative method based on articial neural networks for ndingsolution of a fuzzy equations system. our proposed fuzzied neural network is a ve-layer feed-back neural network that corresponding connection weights to output layer are fuzzy numbers. thisarchitecture of articial neural networks, can get a real input vector and calculates its correspondingfuzzy output. in order to nd the approximate solution of the fuzzy system that supposedly has areal solution, rst a cost function is dened for the level sets of the fuzzy network and target output.then a learning algorithm based on the gradient descent method is used to adjust the crisp inputsignals. the present method is illustrated by several examples with computer simulations.