Root finding and approximation approaches through neural networks

In this paper, we propose two approaches to approximate high order multivariate polynomials and to estimate the number of roots of high order univariate polynomials. We employ high order neural networks such as Ridge Polynomial Networks and Pi -- Sigma Networks, respectively. To train the networks efficiently and effectively, we recommend the application of stochastic global optimization techniques. Finally, we propose a two step neural network based technique, to estimate the number of roots of a high order univariate polynomial.

[1]  R. W. Dobbins,et al.  Computational intelligence PC tools , 1996 .

[2]  De-Shuang Huang,et al.  A Neural Root Finder of Polynomials Based on Root Moments , 2004, Neural Computation.

[3]  Joydeep Ghosh,et al.  The pi-sigma network: an efficient higher-order neural network for pattern classification and function approximation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[4]  R. Storn,et al.  Differential Evolution - A simple and efficient adaptive scheme for global optimization over continuous spaces , 2004 .

[5]  Joydeep Ghosh,et al.  Ridge polynomial networks , 1995, IEEE Trans. Neural Networks.

[6]  Vassilis P. Plagianakos,et al.  Parallel evolutionary training algorithms for “hardware-friendly” neural networks , 2002, Natural Computing.

[7]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[8]  Michael N. Vrahatis,et al.  Recent approaches to global optimization problems through Particle Swarm Optimization , 2002, Natural Computing.

[9]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[10]  Zheru Chi,et al.  Neural networks with problem decomposition for finding real roots of polynomials , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[11]  W. B. Gearhart,et al.  Deflation techniques for the calculation of further solutions of a nonlinear system , 1971 .

[12]  Dimitris K. Tasoulis,et al.  Determining the number of real roots of polynomials through neural networks , 2006, Comput. Math. Appl..