zbMATH — the first resource for mathematics

Solving initial-boundary value problems for systems of partial differential equations using neural networks and optimization techniques. (English) Zbl 1298.65155
Summary: A general system of the time-dependent partial differential equations containing several arbitrary initial and boundary conditions is considered. A hybrid method based on artificial neural networks, minimization techniques and collocation methods is proposed to determine a related approximate solution in a closed analytical form. The optimal values for the corresponding adjustable parameters are calculated. An accurate approximate solution is obtained, that works well for interior and exterior points of the original domain. Numerical efficiency and accuracy of the hybrid method are investigated by two-test problems including an initial value and a boundary value problem for the two-dimensional biharmonic equation.

65M99 Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems
65K10 Numerical optimization and variational techniques
92B20 Neural networks for/in biological studies, artificial life and related topics
Full Text: DOI
[1] Dissanayake, M.W.M.G.; Phan-Thien, N., Neural-network-based approximations for solving partial differential equations, Commun. numer. methods eng., 10, 195-201, (1994) · Zbl 0802.65102
[2] Van Milligen, B.P.; Tribaldos, V.; Jimenez, J.A., Neural network differential equation and plasma equilibrium solver, Phys. rev. lett., 75, 20, 3594-3597, (1995)
[3] Lagaris, I.E.; Likas, A.; Fotiadis, D.I., Artificial neural networks for solving ordinary and partial differential equations, IEEE trans. neural network, 9, 5, 987-1000, (1998)
[4] He, S.; Reif, K.; Unbehauen, R., Multilayer neural networks for solving a class of partial differential equations, Neural network, 13, 385-396, (2000)
[5] Wang, X.; Shimizu, K., Approximate solution of hamilton – jacobi – bellman equation by using neural networks and matrix calculus techniques, IEICE trans. fundam. electron. commun. comput. sci. E, 84-A, 6, 1549-1556, (2001)
[6] Aarts, L.P.; Van der Veer, P., Neural network method for solving partial differential equations, Neural process. lett., 14, 261-271, (2001) · Zbl 0985.68048
[7] Leephakpreeda, T., Novel determination of differential-equation solutions: universal approximation method, J. comput. appl. math., 146, 443-457, (2002) · Zbl 1013.65079
[8] Parisi, D.R.; Mariani, M.C.; Laborde, M.A., Solving differential equations with unsupervised neural networks, Chem. eng. process., 42, 715-721, (2003)
[9] Monterola, C.; Saloma, C., Solving the nonlinear schrodinger equation with an unsupervised neural network: estimation of error in solution, Opt. commun., 222, 331-339, (2003)
[10] Alli, H.; Ucar, A.; Demir, Y., The solutions of vibration control problems using artificial neural networks, J. franklin inst., 340, 307-325, (2003) · Zbl 1032.74564
[11] Sukavanam, N.; Panwar, V., Computation of boundary control of controlled heat equation using artificial neural networks, Int. commun. heat mass transfer, 30, 8, 1137-1146, (2003)
[12] Smaoui, N.; Al-Enezi, S., Modelling the dynamics of nonlinear partial differential equations using neural networks, J. comput. appl. math., 170, 27-58, (2004) · Zbl 1049.65108
[13] Smaoui, N., A hybrid neural network model for the dynamics of the kuramoto – sivashinsky equation, Math. probl. eng., 3, 305-321, (2004) · Zbl 1079.35013
[14] Tassa, Y.; Erez, T., Least squares solutions of the HJB equation with neural-network value-function approximators, IEEE trans. neural network, 18, 4, 1031-1041, (2007)
[15] Filici, C., On a neural approximator to odes, IEEE trans. neural network, 19, 3, 539-543, (2008)
[16] Malek, A.; Shekari Beidokhti, R., Numerical solution for high order differential equations using a hybrid neural network-optimization method, Appl. math. comput., 183, 260-271, (2006) · Zbl 1105.65340
[17] Yentis, R.; Zaghoul, M.E., VLSI implementation of locally connected neural network for solving partial differential equations, IEEE trans. circ. syst. fund. theor. appl., 43, 8, 687-690, (1996)
[18] Haykin, S., Neural networks: A comprehensive foundation, (2007), Prentice-Hall Upper Saddle River, NJ · Zbl 0828.68103
[19] Graupe, D., Principles of artificial neural networks, (2007), World Scientific Singapore · Zbl 1139.68399
[20] Tang, H.; Tan, K.C.; Yi, Z., Neural networks: computational models and applications, (2007), Springer Berlin
[21] Muller, B.; Reinhardt, J.; Strickland, M.T., Neural networks: an introduction, (2002), Springer-Verlag Berlin
[22] Picton, P., Neural networks, (2000), Palgrave Great Britain
[23] Fine, T.L., Feedforward neural network methodology, (1999), Springer-Verlag New York · Zbl 0963.68163
[24] Schalkoff, R.J., Artificial neural networks, (1997), McGraw-Hill New York · Zbl 0910.68165
[25] Ellacott, S.W., Mathematics of neural networks: models, algorithms and applications, (1997), Kluwer Academic Publishers Boston · Zbl 0807.65007
[26] McCulloch, W.S.; Pitts, W., A logical calculus of the ideas immanent in nervous activity, Bull. math. biophys., 5, 115-133, (1943) · Zbl 0063.03860
[27] Hebb, D.O., The organization of behavior, (1949), Wiley New York
[28] Rosenblatt, F., Principles of neurodynamics: perceptrons and the theory of brain mechanisms, (1962), Spartan Books Washington, DC · Zbl 0143.43504
[29] McClelland, J.L.; Rumelhart, D.E., Parallel distributed processing explorations in the microstructure of cognition, vol. 1, (1986), MIT Bradford Press Cambridge, MA
[30] Hornik, K.; Stinchcombe, M.; White, H., Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks, Neural network, 3, 551-560, (1990)
[31] Hornik, K.; Stinchcombe, M.; White, H., Multilayer feedforward networks are universal approximators, Neural network, 2, 5, 359-366, (1989) · Zbl 1383.92015
[32] Kreinovich, V.Y., Arbitrary nonlinearity is sufficient to represent all functions by neural networks: a theorem, Neural network, 4, 381-383, (1991)
[33] Blum, E.K.; Li, L.K., Approximation theory and feed forward networks, Neural network, 4, 511-515, (1991)
[34] Kolmogorov, A.N., On the representation of continuous functions of several variables by superpositions of continuous functions of one variable and addition, Dokl. akad. nauk SSSR, 114, 953-956, (1957), (English Translation: Am. Math. Soc. Transl. 28 (2) (1963) 55-59) · Zbl 0090.27103
[35] Sprecher, D.A., On the structure of continuous functions of several variables, Trans. amer. math. soc., 115, 340-355, (1965) · Zbl 0142.30401
[36] Lorentz, G.G., Approximation of functions, athena series: selected topics in mathematics, Holt, (1966), Rinehart and Winston New York
[37] Lippmann, R.P., An introduction to computing with neural nets, IEEE ASSP mag., 4-22, (1987)
[38] Cybenko, G., Approximation by superpositions of a sigmoidal function, Math. control signals syst., 2, 4, 304-314, (1989) · Zbl 0679.94019
[39] McKeown, J.J.; Stella, F.; Hall, G., Some numerical aspects of the training problem for feed-forward neural nets, Neural network, 10, 8, 1455-1463, (1997)
[40] Gindikin, S.G.; Volevich, L.R., Mixed problem for partial differential equations with quasihomogeneous principal part, (1996), American Mathematical Society Providence, RI · Zbl 0856.35001
[41] Atkinson, K.; Han, W., Theoretical numerical analysis: a functional analysis framework, (2005), Springer-Verlag New York · Zbl 1068.47091
[42] Kincaid, D.R.; Cheney, E.W., Numerical analysis: mathematics of scientific computing, (2002), Brooks/Cole Pacific Grove, CA
[43] Likas, A.; Karras, D.A.; Lagaris, I.E., Neural-network training and simulation using a multidimensional optimization system, Int. J. comput. math., 67, 33-46, (1998) · Zbl 0892.68086
[44] Van der Smagt, P., Minimization methods for training feedforward neural networks, Neural network, 7, 1, 1-11, (1994)
[45] Lurie, S.A.; Vasiliev, V.V., The biharmonic problem of the theory of elasticity, (1995), Gordon & Breach Science Canada · Zbl 0924.73007
[46] Malek, A.; Phillips, T.N., Pseudospectral collocation methods for fourth-order differential equations, IMA J. numer. anal., 15, 523-553, (1995) · Zbl 0855.65088
[47] Phillips, T.N.; Malek, A., Multidomain collocation methods for the stream function formulation of the navier – stokes equations, SIAM J. sci. comput., 16, 4, 773-797, (1995) · Zbl 0832.76074
[48] Malek, A., Pseudospectral analysis for the solution of nonlinear partial differential equations, Nonlinear anal. theory methods appl., 30, 8, 4805-4809, (1997) · Zbl 0892.35009
[49] Nelder, J.A.; Mead, R., A simplex method for function minimization, Comput. J., 7, 308-313, (1965) · Zbl 0229.65053
[50] Lagarias, J.C.; Reeds, J.A.; Wright, M.H.; Wright, P.E., Convergence properties of the nelder – mead simplex method in low dimensions, SIAM J. optim., 9, 1, 112-147, (1998) · Zbl 1005.90056
[51] Reddy, B.D., Introductory functional analysis with applications to boundary value problems and finite elements, (1998), Springer-Verlag New York · Zbl 0893.46002
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.