A. Jafarian - Department of Mathematics‎, ‎Urmia Branch‎, ‎Islamic Azad University‎, ‎Urmia‎, ‎Iran‎.
R. Saneifard - Department of Mathematics‎, ‎Urmia Branch‎, ‎Islamic Azad University‎, ‎Urmia‎, ‎Iran‎.

In current research, an architecture of hybrid articial neural networks has been employed to solve a special kind of fuzzy systems. The proposed four-layer fuzzied recurrent network can approximate real solution of the present fuzzy system to any desired degree of accuracy. To do this, a back-propagation learning rule based on the gradient descent method is designed to estimate the unknowns. Finally, some numerical experiments with comparison are presented to show the effectiveness of the recurrent back-propagation method.In current research, an architecture of hybrid articial neural networks has been employed to solve a special kind of fuzzy systems. The proposed four-layer fuzzied recurrent network can approximate real solution of the present fuzzy system to any desired degree of accuracy. To do this, a back-propagation learning rule based on the gradient descent method is designed to estimate the unknowns. Finally, some numerical experiments with comparison are presented to show the effectiveness of the recurrent back-propagation method.

System of fuzzy polynomials, Fuzzy recurrent neural networks, Approximate solution, Back-propagation learning algorithm