Skip to main content
    • Aa
    • Aa

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

The research of K. Goulianas, A. Margaris, I. Refanidis, K. Diamantaras and T. Papadimitriou has been co-financed by the European Union (European Social Fund – ESF) and Greek national funds through the Operational Program “Education and Lifelong Learning” of the National Strategic Reference Framework (NSRF) – Research Funding Program: THALES, Investing in knowledge society through the European Social Fund.

Linked references
Hide All

This list contains references from the content that can be linked to their source. For a full set of references and notes please see the PDF or HTML where available.

[1] A. R. Barron (1933) Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39 (3), 930945.

[2] C. G. Broyden (1965) A class of methods for solving nonlinear simultaneous equations. Math. Comput. 19 (92), 577593.

[3] C. G. Broyden , J. E. Dennis & J. J. More (1993) On the local and the superlineal convergences of quasi-Newton methods. J. Inst. Math. Appl. 12 (3), 223246.

[7] D. Costarelli (2015) Neural network operators: Constructive interpolation of multivariate functions. Neural Netw. 67, 2836.

[8] D. Costarelli & G. Vinti (2016) Max-product neural network and quasi interpolation operators activated by sigmoidal functions. J. Approx. Theory 209, 122.

[9] D. Costarelli & G. Vinti (2016) Pointwise and uniform approximation by multivariate neural network operators of the max-product type. Neural Netw. 81, 8190.

[10] D. Costarelli & G. Vinti (2016) Approximation by max-product neural network operators of Kantorovich type. Results Math. 69 (3), 505519.

[11] J. E. Dennis & H. Wolkowicz (1993) Least change secant method, sizing and shifting. SIAM J. Numer. Anal. 30 (5), 12911314.

[17] A. Iliev , N. Kyurkchiev & S. Markov (2015) On the approximation of the cut and step functions by logistic and Gompertz functions. BIOMATH 4 (2), 112.

[18] C. Karr L, Weck, B. & L. M. Freeman (1998) Solution to systems of nonlinear equations via a generic algorithm. Eng. Appl. Artif. Intell. 11, 369375.

[21] D. Manocha (1994) Solving Systems of polynomial equations. IEEE Comput. Graph. Appl. 14 (2), 4655.

[22] A. Margaris & K. Goulianas (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] J. M. Martinez (1994) Algorithms for solving nonlinear systems of equations. In: Continuous Optimization: The State of the Art, Kluwer, pp. 81108.

[28] T. T. Nguyen (1993) Neural network architecture of solving nonlinear equation systems. Electron. Lett. 29 (16), 14031405.

[29] H. A. Oliveira & A. Petraglia (2013) Solving nonlinear systems of functional equations with fuzzy adaptive simulated annealing. Appl. Soft Comput. 13 (11), 43494357.

[30] J. M. Ortega & W. C. Rheinboldt (1970) Iterative Solution of Nonlinear Equations in Several Variables, Academic Press, New York.

[32] J. Schmidhuber (2015) Deep learning in neural networks: An overview. Neural Netw. 61, 85117.

[33] E. Spedicato & Z. Huang (1997) Numerical experience with Newton-like methods for nonlinear algebraic systems. Computing 58 (1), 6989.

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: 9 *
Loading metrics...

Abstract views

Total abstract views: 77 *
Loading metrics...

* Views captured on Cambridge Core between 20th June 2017 - 24th July 2017. This data will be updated every 24 hours.