Neural networks have already been successfully applied to model the real world problems. The main aim of this paper is to offer an efficient bivariate interpolation methodology that is based on the artificial neural networks. To do this, a multi-layer feed-forward neural network on the real set points is used. The proposed neural network architecture is able to approximate the unknown interpolating polynomial’s coefficients by using a learning algorithm which is based on the gradient descent method. Finally, to demonstrate the efficiency and accuracy of the proposed method, some test problems in comparison with former techniques, are considered. Keywords Bivariate interpolating polynomial Approximate solution Feed-forward neural network Cost function Learning algorithm
|