The effect of the threshold function for design feed forward neural network for solving Partial differential equations


  • Dr.Khalid. Mindeel. M Al-Abrahemee sity of AL-Qadisiyha



partial differential equations, , Artificial neural network, Levenbrg- Marquardt training., feed forward neural network


In this paper we disperse the outcome of threshold functions for designate feed forward neural network for solution partial differential equationsâ€. “We utility a multi-layer network having one hidden layer with 7 hidden units (neurons) and one linear output unit with different of threshold function of each unit are logsig , tansig, purelin, tribas and hardlim and use Levenberg – Marquardt (trainlm) training algorithmic ruleâ€. Finally the terminate of numerical experience are compare to with the true solution in illustrative examples to ratify the precision and effectiveness of the immediate plan


Download data is not yet available.


BARRON, A. R., Universal approximation bounds for superposition of a sigmoidal function, IEEE Trans. on Information Theory, 39. DOI:

CYBENKO, G., Approximation by superposition of sigmoidal functions,Mathematics of Control, Signals and Systems, 2, # 4 (1989), 303-314. DOI:

HORNIK, K., STINCHCOMBE, M. AND WHITE, H . , Multilayer feedforward networks are universal approximators, Neural Networks, 2 (1989),359-366. DOI:

MHASKAR, H. N. AND MICCHELLI, C. A. , Approximation by superposition of asigmoidal function and radial basis functions, Advances in Applied Mathematics, 13 (1992),350-373 . DOI:

Schalkoff, R.J. (1997) Artificial Neural Networks.McGraw-Hill, New York.

Picton, P. (2000) Neural Networks. 2nd ed. Palgrave, Great Britain.

Rosenblatt, F. (1957) The perceptron - a perceiving and recognizing automation. Comell Aeronautical Laboratory, Report 85–460.

Lee, H. and kang, I.S., Neural algorithms for solving differential equations, journal of computational physics 91 (1990) 110-131. DOI:

Meade Jr, A.J. and Fernandez, A.A., The numerical solution of linear ordinary differential equations by feed forward neural networks, Mathematical and Computer Modelling 19(12) (1994), 1 -25. DOI:

Meade Jr, A.J. and Fernandez, A.A., Solution of nonlinear ordinary differential equations by feedforward neural networks, Mathematical and Computer Modelling 20 (9)(1994)19-44. DOI:

Dissanayake, M.W.M.G. and Phan-Thien, N., Neural network based approximations forsolving partial differential equations, Communications in Numerical Methods in Engineering 10 (1994) 195-201. DOI:

Lagaris, I.E. and Likas, Fotiadis, A, D.I., Artificial neural networks for solving ordinary and partial differential equations, IEEE Transactions on Neural Networks 9 (5)(1998) 987-1000.

Pai, G. V and Rajasekaran, S, (2006), ‘Neural Networks, Fuzzy Logic and Genetic Algorithms Synthesis and Applications’, 6th ed, Prentice Hall of India Pvt. Ltd.

Bekir Karlik and A Vehbi Olgac ,Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks, International Journal of Artificial Intelligence And Expert Systems (IJAE), 1(2010),111-122.

B. M. wilamowski and S. Iplikei, an Algorithm for fast convergence in training neural network, IEEE.(2001):1778-1782.

M. Kameswar Rao And K.P. Ravindran, An Evolutionary Approach For Solving differential Equations,2011.

I. E. Lagaris, A. Likas and D. I. Fotiadis , Artificial Neural Net works for Solving Ordinary and Partial Differential Equations,1997. DOI:




How to Cite

Al-Abrahemee, D. M. M. (2017). The effect of the threshold function for design feed forward neural network for solving Partial differential equations. Journal of Kufa for Mathematics and Computer, 4(1), 13–22.

Similar Articles

1 2 3 4 5 6 > >> 

You may also start an advanced similarity search for this article.