Abstract
In this paper, we test the methods and algorithms for constructing neural network models from equations and data using the example of the problem on the restoration of the Laplace equation solutions according to the measurements in a unit square. We estimate the quality of approximate solutions constructed with the help of neural networks for different sets of system parameters (the number of points in which the operator is calculated, the number of test points on one side of the square). During the experiment, all test points inside the square are regenerated. Selection of the solution is carried out by optimization of the error functional. Optimization is carried out using the algorithm of training neural networks Resilient Propagation (RProp). The algorithms considered can be applied to a wide range of practically interesting problems, since they practically do not depend on the form of the differential equation, its linearity, the geometry of the region, etc.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
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)
Rostami, F., Jafarian, A.: A new artificial neural network structure for solving high-order linear fractional differential equations. Int. J. Comput. Math. 95(3), 528–539 (2018)
Zuniga-Aguilar, C.J., Coronel-Escamilla, A., Gomez-Aguilar, J.F., Alvarado-Martinez, V.M., Romero-Ugalde, H.M.: New numerical approximation for solving fractional delay differential equations of variable order using artificial neural networks. Eur. Phys. J. Plus 133(2), 1–16 (2018)
Yadav, N., Yadav, A., Kumar, M.: Introduction to Neural Network Methods for Differential Equations. SpringerBriefs in Applied Sciences and Technology, Computational Intelligence. Springer, Dordrecht (2015)
Mall, S., Chakraverty, S.: Single layer Chebyshev neural network model for solving elliptic partial differential equations. Neural Process. Lett. 45(3), 825–840 (2017)
Tarkhov, D.A., Vasilyev, A.N.: New neural network technique to the numerical solution of mathematical physics problems. I: Simple problems. Opt. Memory 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 Patents Eng. 11(1), 10–15 (2017)
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., Liu, Q., Ronzhin, A. (eds.) Advances in Neural Networks. 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. Memory Neural Netw. 26(2), 96–109 (2017)
Acknowledgment
This paper is based on research carried out with the financial support of the grant of the Russian Scientific 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
Tarkhov, D.A., Migovan, M.A., Ivanenko, K.A., Smirnov, S.A., Kobicheva, A.M. (2019). The Problem of Solution Restoration by Measurements for the Laplace Equation. In: Antipova, T., Rocha, A. (eds) Digital Science. DSIC18 2018. Advances in Intelligent Systems and Computing, vol 850. Springer, Cham. https://doi.org/10.1007/978-3-030-02351-5_51
Download citation
DOI: https://doi.org/10.1007/978-3-030-02351-5_51
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-02350-8
Online ISBN: 978-3-030-02351-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)