[KSCI] Korea Science Citation Index Service

http://dx.doi.org/10.9708/jksci.2021.26.01.069

The Possibility of Neural Network Approach to Solve Singular Perturbed Problems

Kim, Jee-Hyun (Dept. of Software Engineering, Seoil University)
Cho, Young-Im (Dept. of Computer Engineering, Gachon University)

Publication Information

Journal of the Korea Society of Computer and Information / v.26, no.1, 2021 , pp. 69-76 More about this Journal

Abstract

Recentlly neural network approach for solving a singular perturbed integro-differential boundary value problem have been researched. Especially the model of the feed-forward neural network to be trained by the back propagation algorithm with various learning algorithms were theoretically substantiated, and neural network models such as deep learning, transfer learning, federated learning are very rapidly evolving. The purpose of this paper is to study the approaching method for developing a neural network model with high accuracy and speed for solving singular perturbed problem along with asymptotic methods. In this paper, we propose a method that the simulation for the difference between result value of singular perturbed problem and unperturbed problem by using neural network approach equation. Also, we showed the efficiency of the neural network approach. As a result, the contribution of this paper is to show the possibility of simple neural network approach for singular perturbed problem solution efficiently.

Keywords

Neural Network; Back Propagation; Singular Perturbed Problems; Integro-differential Boundary Value Problems; Training Algorithm;

Citations & Related Records

Reference

1	D. Nurgabyl, "Asymptotic estimates for the solution of a restoration problem with initial jump," J. Appl. Math. pp.1-11. 2014.
2	K. A. Kasymov, M. K. Dauylbaev, "On the estimation of solutions of the Cauchy problem with an initial jump of any order for linear singularly perturbed integro-differential equations," Differ. Equ. 35, pp.822-830, 1999.
3	S. Chakraverty, S. Mall, "Artificial Neural Networks for Engineers and Scientists: Solving Ordinary Differential Equations," Boca Raton:CRC Press, 2017.
4	K. A. Kasymov, "Singularly perturbed boundary value problems with initial jumps," Sanat, Almaty, 1997.
5	M. I. Vishik, L. A. Lyusternik, "On the initial jump for nonlinear differential equations con-taining a small parameter," Doklady Akademi Nauk SSSR no.132, vol.6, pp.1242-1245, 1960.
6	M. I. Imanaliev, "Asymptotic methods in the theory of singularly perturbed integro-differen-tial systems," Ilim, Frunze, 1972.
7	S. A. Lomov, "Introduction to the General Theory of Singular Perturbations," Nauka: Moscow, Russia, 1981.
8	A. Zhumanazarova, YICho, "Asymptotic convergence of the solution of a singularly perturbed integro-differential boundary value problem," Mathematics, Aug. 2020.
9	P. E. Gill, W. Murray and M. H. Wright, "Practical Optimization," London, Academic Press Inc., 1981.
10	D. A. Tursunov, K. G. Kozhobekov, "Asymptotics of the solution of singularly perturbed differential equations with a fractional turning point," Izv. Irk.Gos.Univ. 21, 108-121. Jan. 2017.
11	L. N. M. Tawfiq and K. M. M. Al-Abrahemee, "Design Neural Network to Solve Singular Pertubation Problems," J. of Applied & Computational Mathematics, vol.3, US: OMICS Int., pp.1-5, Mar. 2014.
12	A. Kh. Nayfe, "Perturbation methods," Mir, Moscow, 1976.
13	L. N. M. Tawfiq and Kh. Mohammed, "Design Collocation Neural Network to Solve Singular Perturbed Problems with Initial Conditions," Inter. J. of Modern Engineering Sciences, vol.3, USA: Modern Scientific Press, pp.29-38, May 2014.
14	A. M. Zhumanazarova, YICho, "Asymptotic Convergence of the Solution of a Singularly Perturbed Integro-Differential Boundary Value Problem," Mathematics, vol.8, Switzerl.: MDPI, pp.1-17, Feb. 2020. DOI
15	J. K. Hunter, "Asymptotic Analysis and Singlular Perturbation Theory," Dept. of Mathematics, Univ. of California at Davis, Feb. 2004.
16	T. Watkins, "Perturbation Analysis: Regular and Singular," San Jose State University, https://www.sjsu.edu/faculty/watkins/perturbregsing.htm
17	A. B. Vasilyeva, V. E. Butuzov, "Asymptotic Methods in the Theory of Singular Perturbations," Moskow: Visshaya shkola, 1990.
18	F. Wassermann, "Neurocomputer Techniques: Theory and Practice," Mir, Moscow, 1992.
19	A. B. Vasilyeva, V. F. Butuzov, "Asymptotic methods in the theory of singular perturbations," Visshaya shkola, Moscow, 1990.
20	E. A. Hussain and N. S. M. Al-Saif, "Design Feed Forward Neural Network for Solving Two Dimension Singularly Perturbed Integro-Differential and Integral Equation," Inter. J. of Applied Mathematical Research, vol.2, UAE: Sci.Publish. Corp., pp.134-139, 2013.