پديدآورندگان :
Ghaderi Amin amin.g.ghaderi@gmail.com Department of Computer Sciences, Shahid Beheshti University, G.C., Tehran, Iran , Parand Kourosh k_parand@sbu.ac.ir Department of Cognitive Modelling, Institute for Cognitive and Brain Sciences, Shahid Beheshti University, G.C., Tehran, Iran , Abdar Moloud m.abdar1987@gmail.com School of Computer Science and Engineering, The University of Aizu, Japan
كليدواژه :
Bessel Neural Network , Feed forward Neural Network , Error back Propagation method , Singular initial value problem
چكيده فارسي :
The present paper introduces a new Bessel Artificial Neural Network (BeNN) approach to solve Lane-Emden type equations, which are second order non-linear singular initial value ordinary differential problems. A single layer Feed-Forward Neural Network as unsupervised method is utilized and the hidden layer is removed by using a series expansion of Bessel polynomials. We also applied the error back propagation learning algorithm for minimizing the computed Mean Square Error (MSE) function and amending the Neural Network parameters (weights) without direct utilization of other optimization methods. In terms of accuracy and efficiency of the present learning approach by a few basis of Bessel polynomials, the obtained outcomes are compared with some other numerical results.
