Abstract
In this paper, we continue to study our neural network (NN) approach to the construction of approximate solutions of boundary value problems for partial differential equations. We test the NN learning algorithms on the example of the Dirichlet problem for the Laplace equation in the unit square. We do not use linearity and other features of the Laplace equation; therefore we expect the similar behavior of the algorithms under study for other problems. In the first algorithm, we use a constant number of neurons and train the entire network at once. The second and third algorithms are evolutionary ones, i.e., the structure of the NN (the number of neurons) changes in the learning process. In the second algorithm, we add neurons one by one through a certain number of training steps and conduct additional training of the entire resulting NN. In the third algorithm, we add neurons in the same way, but the learning process is only for the last added neuron. In all series, we use the maximum number of neurons equal to 10, which was enough to achieve an acceptable quality of training. We estimate the quality of NN training by the error functional consisting of two terms which are responsible for satisfying the equation and boundary conditions. These summands are calculated on the set of trial points (TP). We compared the quality of NN training in the case of constant TP and the application of the proposed procedure of re-generation of TP. Computational experiments have shown that the procedure of TP re-generation with a small number of them allows reducing the error by order of magnitude.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Lagaris, I.E., Likas, A., Fotiadis, D.I.: Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans. Neural Netw. 9(5), 987–1000 (1998)
Dissanayake, M.W.M.G., Phan-Thien, N.: Neural-network-based approximations for solving partial differential equations. Commun. Numer. Methods Eng. 10(3), 195–201 (1994)
Fasshauer, G.E.: Solving differential equations with radial basis functions: multilevel methods and smoothing. Adv. Comput. Math. 11, 139–159 (1999)
Förnberg, B., Larsson, E.: A numerical study of some radial basis function based solution methods for elliptic PDEs. Comput. Math. Appl. 46, 891–902 (2003)
Gorbachenko, V.I., Zhukov, M.V.: Solving boundary value problems of mathematical physics using radial basis function networks. Comput. Math. Math. Phys. 57(1), 145–155 (2017)
Tarkhov, D.A., Vasilyev, A.N.: New neural network technique to the numerical solution of mathematical physics problems. I: simple problems. Opt. Mem. Neural Netw. (Inf. Opt.) 14(1), 59–72 (2005)
Lazovskaya, T.V., Tarkhov, D.A., Vasilyev, A.N.: Parametric neural network modeling in engineering. Recent. Pat. Eng. 11(1), 10–15 (2017)
Lazovskaya, T., Tarkhov, D.: Multilayer neural network models based on grid methods. IOP Conference Series: Materials Science and Engineering, vol. 158 (2016). http://iopscience.iop.org/article/10.1088/1757-899X/158/1/01206
Gorbachenko, V.I., Lazovskaya, T.V., Tarkhov, D.A., Vasilyev, A.N., Zhukov, M.V.: Neural network technique in some inverse problems of mathematical physics. In: Cheng, L., et al. (eds.) ISNN 2016. LNCS, vol. 9719, pp. 310–316. Springer, Cham (2016)
Budkina, E.M., Kuznetsov, E.B., Lazovskaya, T.V., Tarkhov, D.A., Shemyakina, T.A., Vasilyev, A.N.: Neural network approach to intricate problems solving for ordinary differential equations. Opt. Mem. Neural Netw. 26(2), 96–109 (2017)
Vasilyev, A.N., Tarkhov, D.A., Tereshin, V.A., Berminova, M.S., Galyautdinova, A.R.: Semi-empirical neural network model of real thread sagging. In: Studies in Computational Intelligence, vol. 736, pp. 138–146. Springer (2018)
Acknowledgments
This paper is based on research carried out with the financial support of the grant of the Russian Science Foundation (project no. 18-19-00474).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Galyautdinova, A.R., Sedova, J.S., Tarkhov, D.A., Varshavchik, E.A., Vasilyev, A.N. (2019). Comparative Test of Evolutionary Algorithms to Build an Approximate Neural Network Solution of the Model Boundary Value Problem. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research II. NEUROINFORMATICS 2018. Studies in Computational Intelligence, vol 799. Springer, Cham. https://doi.org/10.1007/978-3-030-01328-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-01328-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01327-1
Online ISBN: 978-3-030-01328-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)