USING FEED-BACK NEURAL NETWORK METHOD FOR SOLVING LINEAR FREDHOLM INTEGRAL EQUATIONS OF THE SECOND KIND

In this paper a new method for finding the solution of Fredholm integral equation based on hybrid neural networks have presented. The proposed neural net can get a real input vector and calculates its corresponding output vector. Next a learning algorithm based on the gradient descent method has been defined for adjusting the connection weights. Eventually, we have showed this method in comparison with some numerical methods provides solutions with good generalization and high accuracy. The method is illustrated by several examples with computer simulations.