Extended Aartificial Neural Networks Approach and Fractional Volterra Integro-Differential Equations
Subject Areas : International Journal of Industrial Mathematicsاحمد جعفریان 1 , رحیم صانعی فرد 2
1 - Department of Mathematics, Urmia Branch, Islamic Azad University, Urmia, Iran.
2 - Department of Mathematics, Urmia Branch, Islamic Azad University, Urmia, Iran.
Keywords: Fuzzy recurrent neural networks, System of fuzzy polynomials, Back-propagation learning algorithm, Approximate solution,
Abstract :
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.