Abstract
A universal approximator, such as multilayer perceptron, is a tool that allows mapping of any multidimensional continuous function. The aim of this paper is to discuss a method of perceptron training that would result in its ability to map the functions constituting the solutions of partial differential equations of first and second order. The developed algorithm has been validated by means of equations whose analytical solutions are known.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lee, H., Kang, I.: Neural algorithms for solving differential equations. Journal of Computional Physics 91, 110–131 (1990)
Dissanayake, M.W.M.G., Phan-Thien, N.: Neural-network-based approximations for solving partial differential equations. Communications in Numerical Methods in Engineering 10, 195–201 (1994)
Meade, A.J., Fernadez, A.A.: Solution of nonlinear ordinary differential equations by feedforward neural networks. Mathematical and Computer Modeling 20(9), 19–44 (1994)
Ramuhalli, P., Udpa, L., Udpa, S.: Finite-element neural networks for solving differential equations. IEEE Transactions on Neural Networks 16(6), 1381–1392 (2005)
Mai-Duy N., Tran-Cong T.: Numerical solution of differential equations using multiquadric radial basis function networks, vol. 14, pp.185–199 (2001)
Mai-Duy, N., Tanner, R.I.: Solving high-order partial differential equations with indirect radial basis function networks. International Journal for Numerical Methods in Engineering 63, 1636–1654 (2005)
Jianyu, L., Siwei, L., Yingjian, Q., Yaping, H.: Numerial solution of elliptic partial differential equation using radial basis function neural networks. Neural Networks 15, 729–734 (2003)
Lagaris, I.E., Likas, A., Fotiadis, I.D.: Artificial neural networks for solving ordinary and partial differentia equation. IEEE Transactions on Neural Networks 9(5), 987–1000 (1998)
Lagaris, I.E., Likas, A.C., Papageorgiou, D.G: Neural-network methods for boundary value problems with irregular boundaries. IEEE Transactions on Neural Networks 11(5), 1041–1049 (2000)
Delpiano, J., Zagers, P.: Semi-autonomus neural network differential equation solver. In: International Joint Conference on Neural Networks, Vancouver, Canada, pp. 1863–1869 (2006)
Wieczorek T., Golak, S.: Advances In Soft Computing. In: Proceedings of the International IIS: IIPWM’04 Conference, pp. 470–474 (2004)
Aarts, L.P., Veer, P.: Neural network method for solving partial differential equations. Neural Processing Letters 14, 261–271 (2001)
Hagan, M.T., Menhaj, M.: Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks 5(6), 989–993 (1994)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Golak, S. (2007). A MLP Solver for First and Second Order Partial Differential Equations. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74695-9_81
Download citation
DOI: https://doi.org/10.1007/978-3-540-74695-9_81
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74693-5
Online ISBN: 978-3-540-74695-9
eBook Packages: Computer ScienceComputer Science (R0)