Skip to main content Accessibility help

Solving polynomial systems using a fast adaptive back propagation-type neural network algorithm

  • K. GOULIANAS (a1), A. MARGARIS (a2), I. REFANIDIS (a3) and K. DIAMANTARAS (a1)

This paper proposes a neural network architecture for solving systems of non-linear equations. A back propagation algorithm is applied to solve the problem, using an adaptive learning rate procedure, based on the minimization of the mean squared error function defined by the system, as well as the network activation function, which can be linear or non-linear. The results obtained are compared with some of the standard global optimization techniques that are used for solving non-linear equations systems. The method was tested with some well-known and difficult applications (such as Gauss–Legendre 2-point formula for numerical integration, chemical equilibrium application, kinematic application, neuropsychology application, combustion application and interval arithmetic benchmark) in order to evaluate the performance of the new approach. Empirical results reveal that the proposed method is characterized by fast convergence and is able to deal with high-dimensional equations systems.

Hide All
[1] Barron, A. R. (1933) Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39 (3), 930945.
[2] Broyden, C. G. (1965) A class of methods for solving nonlinear simultaneous equations. Math. Comput. 19 (92), 577593.
[3] Broyden, C. G., Dennis, J. E. & More, J. J. (1993) On the local and the superlineal convergences of quasi-Newton methods. J. Inst. Math. Appl. 12 (3), 223246.
[4] Burden, R. L., Faires, J. D. & Burden, A. M. (2015) Numerical Analysis, ISBN 978-1305253667, Brooks Cole, Boston, USA.
[5] Cao, F. & Chen, Z. (2009) The approximation operators with sigmoidal functions. Comput. Math. Appl. 58 (4), 758765.
[6] Cao, F. & Chen, Z. (2012) The construction and approximation of a class of neural networks operators with ramp functions. J. Comput. Anal. Appl. 14 (1), 101112.
[7] Costarelli, D. (2015) Neural network operators: Constructive interpolation of multivariate functions. Neural Netw. 67, 2836.
[8] Costarelli, D. & Vinti, G. (2016) Max-product neural network and quasi interpolation operators activated by sigmoidal functions. J. Approx. Theory 209, 122.
[9] Costarelli, D. & Vinti, G. (2016) Pointwise and uniform approximation by multivariate neural network operators of the max-product type. Neural Netw. 81, 8190.
[10] Costarelli, D. & Vinti, G. (2016) Approximation by max-product neural network operators of Kantorovich type. Results Math. 69 (3), 505519.
[11] Dennis, J. E. & Wolkowicz, H. (1993) Least change secant method, sizing and shifting. SIAM J. Numer. Anal. 30 (5), 12911314.
[12] El-Emary, I. M. M. & El-Kareem, M. M. A. (2008) Towards using genetic algorithms for solving nonlinear equation systems. World Appl. Sci. J. 5 (3), 282289.
[13] Goulianas, K., Margaris, A. & Adamopoulos, M. (2013) Finding all real roots of 3 × 3 nonlinear algebraic systems using neural networks. Appl. Math. Comput. 219 (9), 44444464.
[14] Grosan, C., Abraham, A. & Snasel, V. (2012) Solving polynomial systems using a modified line search approach. Int. J. Innovative Comput. Inform. Control 8 (1) (B), 501526.
[15] Grosan, C. & Abraham, A. (2012) Multiple solutions of a system of nonlinear equations. Int. J. Innovative Comput. Inform. Control 4 (9), 21612170.
[16] Hahm, N. & Hong, B. I. (2016) A Note on neural network approximation with a sigmoidal function. Appl. Math. Sci. 10 (42), 20752085.
[17] Iliev, A., Kyurkchiev, N. & Markov, S. (2015) On the approximation of the cut and step functions by logistic and Gompertz functions. BIOMATH 4 (2), 112.
[18] Karr, C. L, Weck, B. & Freeman, L. M. (1998) Solution to systems of nonlinear equations via a generic algorithm. Eng. Appl. Artif. Intell. 11, 369375.
[19] Ko, T. H., Sakkalis, T. & Patrikalakis, N. M. (2004) Nonlinear polynomial systems: Multiple roots and their multiplicities. In: Giannini, F. & Pasko, A. (editors), Proceedings of Shape Modelling International Conference, SMI 2004, Genova, Italy.
[20] Mamat, M., Muhammad, K. & Waziri, M. Y. (2014) Trapezoidal Broyden's method for solving systems of nonlinear equations. Appl. Math. Sci. 8 (6), 251260.
[21] Manocha, D. (1994) Solving Systems of polynomial equations. IEEE Comput. Graph. Appl. 14 (2), 4655.
[22] Margaris, A. & Goulianas, K. (2012) Finding all roots of 2 × 2 non linear algebraic systems using back propagation neural networks. In: Neural Computing and Applications, Vol. 21(5), Springer-Verlag London Limited, pp. 891904.
[23] Martinez, J. M. (1994) Algorithms for solving nonlinear systems of equations. In: Continuous Optimization: The State of the Art, Kluwer, pp. 81108.
[24] Martynyuk, A. A. (2008) An exploration of polydynamics of nonlinear equations on time scales. ICIC Exp. Lett. 2 (2), 155160.
[25] Mathia, K. & Saeks, R. (1995) Solving nonlinear equations using reccurent neural networks. In: World Congress on Neural Networks (WCNN'95), Washington DC, pages I-76 to I-80.
[26] Mhetre, P. (2012) Genetic algorithm for linear and nonlinear equation. Int. J. Adv. Eng. Technol. 3 (2), 114118.
[27] Mishra, D. & Kalra, P. (2007) Modified hopfield neural network approach for solving nonlinear algebraic equations. Eng. Lett. 14 (1), 135142.
[28] Nguyen, T. T. (1993) Neural network architecture of solving nonlinear equation systems. Electron. Lett. 29 (16), 14031405.
[29] Oliveira, H. A. & Petraglia, A. (2013) Solving nonlinear systems of functional equations with fuzzy adaptive simulated annealing. Appl. Soft Comput. 13 (11), 43494357.
[30] Ortega, J. M. & Rheinboldt, W. C. (1970) Iterative Solution of Nonlinear Equations in Several Variables, Academic Press, New York.
[31] Rheinboldt, W. C. (1974) Methods for solving systems of equations. Reg. Conf. Ser. Appl. Math 14.
[32] Schmidhuber, J. (2015) Deep learning in neural networks: An overview. Neural Netw. 61, 85117.
[33] Spedicato, E. & Huang, Z. (1997) Numerical experience with Newton-like methods for nonlinear algebraic systems. Computing 58 (1), 6989.
[34] Zhou, G. & Zhu, P. (2010) Iterative algorithms for solving repeated root of nonlinear equation by modified Adomian decomposition method. ICIC Exp. Lett. 4 (2), 595600.
[35] Zhoug, X., Zhang, T. & Shi, Y. (2009) Oscillation and nonoscillation of neutral difference equation, with positive and negative coefficients. Int. J. Innovative Comput. Inform. Control 5 (5), 13291342.
Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

European Journal of Applied Mathematics
  • ISSN: 0956-7925
  • EISSN: 1469-4425
  • URL: /core/journals/european-journal-of-applied-mathematics
Please enter your name
Please enter a valid email address
Who would you like to send this to? *



Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed