Abstract
The authors present a method to solve differential equations with any kind of initial and boundary conditions using the Fibonacci neural network (FNN). Fibonacci polynomial has been used as an activation function in the middle layer to construct the FNN. The trial solution of the differential equation is considered as the output of the feed-forward neural network, which consists of adjustable parameters (weights). The weights are adjusted with Newtons’ like method for equality constraints. The authors have also shown the stability and convergence of the weights with iteration through the graphs. The application of the current method is range from single ordinary differential equations (ODEs) to system of ODE’s. The authors have implemented the method to solve a variety of differential equations and established the exactness of the current method by comparison of the solution obtained by previously solved methods.
Similar content being viewed by others
Data availability statement
This manuscript has no associated data.
References
Ahmad I, Raja MAZ, Bilal M, Ashraf F (2016) Bio-inspired computational heuristics to study Lane–Emden systems arising in astrophysics model. SpringerPlus 5(1):1866
Bélair J, Campbell SA, van den Driessche P (1996) Frustration, stability, and delay-induced oscillations in a neural network model. SIAM J Appl Math 56(1):245–255
Bertsekas DP (2014) Constrained Optimization and Lagrange Multiplier Methods. Academic Press, Cambrdige
Chakraverty S, Mall S (2014) Regression-based weight generation algorithm in neural network for solution of initial and boundary value problems. Neural Comput Appl 25(3–4):585–594
Hatamzadeh-Varmazyar S, Masouri Z (2018) An efficient numerical algorithm for solving linear differential equations of arbitrary order and coefficients. Int J Ind Math 10(2):131–142
He S, Reif K, Unbehauen R (2000) Multilayer neural networks for solving a class of partial differential equations. Neural Netw 13(3):385–396
Khudair AR, Haddad S, Khalaf SL et al (2016) Mean square solutions of second-order random differential equations by using the differential transformation method. Open J Appl Sci 6(04):287
Kumar M, Yadav N (2011) Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: a survey. Comput Math Appl 62(10):3796–3811
Lee H, Kang IS (1990) Neural algorithm for solving differential equations. J Comput Phys 91(1):110–131
Lyu P, Vong S (2020) An efficient numerical method for q-fractional differential equations. Appl Math Lett 103:106156
Mall S, Chakraverty S (2014) Chebyshev neural network based model for solving Lane–Emden type equations. Appl Math Comput 247:100–114
Mall S, Chakraverty S (2016) Application of legendre neural network for solving ordinary differential equations. Appl Soft Comput 43:347–356
McFall KS, Mahan JR (2009) Artificial neural network method for solution of boundary value problems with exact satisfaction of arbitrary boundary conditions. IEEE Trans Neural Netw 20(8):1221–1233
Pakdaman M, Ahmadian A, Effati S, Salahshour S, Baleanu D (2017) Solving differential equations of fractional order using an optimization technique based on training artificial neural network. Appl Math Comput 293:81–95
Raja MAZ, Khan JA, Qureshi IM (2010) A new stochastic approach for solution of Riccati differential equation of fractional order. Ann Math Artif Intell 60(3–4):229–250
Reddy JN (1993) An introduction to the finite element method, vol 27. McGraw-Hill Education, New York
Tsoulos IG, Gavrilis D, Glavas E (2009) Solving differential equations with constructed neural networks. Neurocomputing 72(10–12):2385–2391
Wambecq A (1978) Rational Runge–Kutta methods for solving systems of ordinary differential equations. Computing 20(4):333–342
Wazwaz A-M (2001) A new algorithm for solving differential equations of Lane–Emden type. Appl Math Comput 118(2–3):287–310
Yazdi HS, Pakdaman M, Modaghegh H (2011) Unsupervised kernel least mean square algorithm for solving ordinary differential equations. Neurocomputing 74(12–13):2062–2071
Zúñiga-Aguilar C, Romero-Ugalde H, Gómez-Aguilar J, Escobar-Jiménez R, Valtierra-Rodríguez M (2017) Solving fractional differential equations of variable-order involving operators with Mittag–Leffler kernel using artificial neural networks. Chaos Solitons Fractals 103:382–403
Acknowledgements
José Francisco Gómez Aguilar acknowledges the support provided by CONACyT: Cátedras CONACyT para jóvenes investigadores 2014 and SNI-CONACyT.
Author information
Authors and Affiliations
Contributions
KDD: conceptualization, methodology, writing—original draft, and supervision. JFG-A: conceptualization, methodology, writing—original draft preparation, and supervision. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Communicated by Jose Alberto Cuminato.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Dwivedi, K.D., Gómez-Aguilar, J.F. An efficient numerical method to solve ordinary differential equations using Fibonacci neural networks. Comp. Appl. Math. 42, 54 (2023). https://doi.org/10.1007/s40314-023-02197-x
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40314-023-02197-x