Abstract
The numerical solution of problems based on ordinary and partial differential equations has been a subject of extensive research. While several methods, such as the finite difference, finite element, and finite volume methods, have been developed, each has its own strengths and limitations. This paper presents a different approach that utilizes feedforward neural networks to approximate functions, resulting in a differentiable analytical expression. Compared to other methods, this approach requires significantly fewer model parameters, leading to reduced computational requirements. The study examines the influence of a neural network’s loss function configuration on the accuracy and convergence rate of solving partial differential equations for functions of two variables: coordinate and time, using the example of the Fisher’s equation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Samarskii, A.A., Volosevich, P.P., Volchinskaya, M.I., Kurdyumov, S.P.: A finite-difference method for the solution of one-dimensional non-stationary problems in magneto-hydrodynamics. USSR Comput. Math. Math. Phys. 8(5), 117–134 (1968)
Bressloff, P.C., Coombes, S.: Dynamics of strongly coupled spiking neurons. Neural Comput. 12(1), 91–129 (2000)
Greenspan, H.P.: Models for the growth of a solid tumor by diffusion. Stud. Appl. Math. 51(4), 317–340 (1972)
Samarskii, A.A., Nikolaev, E.S.: Methods for solving grid equations (1978)
Zienkiewicz, O.C., Morice, P.B.: The Finite Element Method in Engineering Science, vol. 1977. McGraw-Hill, London (1971)
Kovenya, V.M., Chirkov, D.V.: Methods of Finite Differences and Finite Volumes for Solving Problems of Mathematical Physics, pp. 7–8. Novosibirsk State University, Novosibirsk (2013)
Lagaris, I.E., Likas, A., Fotiadis, D.I.: Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans. Neural Networks 9(5), 987–1000 (1998)
Ladygin, S.A., Karachurin, R.N., Ryabov, P.N.: Numerical approach for studying problems for differential equations based on neural network method. In: IX International Conference “Laser, Plasma Research and Technologies” LaPlaz-2023: Proceedings, Conference Series LaPlaz, Publisher National Research Nuclear University MEPhI (Moscow), Abstracts, p. 147 (2023)
Ladygin, S.A., Karachurin, R.N., Ryabov, P.N., Kudryashov, N.A.: On the features of a numerical approach based on neural networks with direct communication for solving problems for differential equations. Phys. Atomic Nuclei (in press)
Wu, G., Wang, F., Qiu, L.: Physics-informed neural network for solving Hausdorff derivative Poisson equations. Fractals, 2340103 (2023)
Uddin, Z., Ganga, S., Asthana, R., Ibrahim, W.: Wavelets based physics informed neural networks to solve non-linear differential equations. Sci. Rep. 13(1), 2882 (2023)
Fang, Y., Wu, G.Z., Kudryashov, N.A., Wang, Y.Y., Dai, C.Q.: Data-driven soliton solutions and model parameters of nonlinear wave models via the conservation-law constrained neural network method. Chaos Solitons Fractals 158, 112118 (2022)
Fisher, R.A.: The wave of advance of advantageous genes. Ann. Eugen. 7(4), 355–369 (1937)
Kolmogorov, A.: Étude de l’équation de la diffusion avec croissance de la quantité de matière et son application á un problème biologique. Moscow Univ. Bull. Math. 1, 1–25 (1937)
Ketkar, N., Moolayil, J., Ketkar, N., Moolayil, J.: Automatic differentiation in deep learning. In: Learn Best Practices of Deep Learning Models with PyTorch, Deep Learning with Python, pp. 133–145 (2021)
Kudryashov, N.A.: One method for finding exact solutions of nonlinear differential equations. Commun. Nonlinear Sci. Numer. Simul. 17(6), 2248–2253 (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Karachurin, R., Ladygin, S., Ryabov, P., Shilnikov, K., Kudryashov, N. (2024). Exploring the Efficiency of Neural Networks for Solving Dynamic Process Problems: The Fisher Equation Investigation. In: Samsonovich, A.V., Liu, T. (eds) Biologically Inspired Cognitive Architectures 2023. BICA 2023. Studies in Computational Intelligence, vol 1130. Springer, Cham. https://doi.org/10.1007/978-3-031-50381-8_53
Download citation
DOI: https://doi.org/10.1007/978-3-031-50381-8_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-50380-1
Online ISBN: 978-3-031-50381-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)