Abstract
This paper introduces a new algorithm for solving ordinary differential equations (ODEs) with initial or boundary conditions. In our proposed method, the trial solution of differential equation has been used in the regression-based neural network (RBNN) model for single input and single output system. The artificial neural network (ANN) trial solution of ODE is written as sum of two terms, first one satisfies initial/boundary conditions and contains no adjustable parameters. The second part involves a RBNN model containing adjustable parameters. Network has been trained using the initial weights generated by the coefficients of regression fitting. We have used feed-forward neural network and error back propagation algorithm for minimizing error function. Proposed model has been tested for first, second and fourth-order ODEs. We also compare the results of proposed algorithm with the traditional ANN algorithm. The idea may very well be extended to other complicated differential equations.
Similar content being viewed by others
References
Ricardo HJ (2009) A modern introduction to differential equations, 2nd edn. Elsevier, Amsterdam
Sneddon IN (2006) Elements of partial differential equations. Dover, New York
Douglas J, Jones BF (1963) Predictor–corrector methods for nonlinear parabolic differential equations. J Ind Appl Math 11:195–204
Reddy JN (1993) An introduction to the finite element method. McGraw-Hill, New York
Meade AJ Jr, Fernandez AA (1994) The numerical solution of linear ordinary differential equations by feed forward neural networks. Math Comput Model 19:1–25
Meade AJ Jr, Fernandez AA (1994) Solution of nonlinear ordinary differential equations by feed forward neural networks. Math Comput Model 20:19–44
Lagaris IE, Likas AC, Fotiadis DI (1998) Artificial neural networks for solving ordinary and partial differential equations. IEEE Trans Neural Netw 9:987–1000
Lagaris IE, Likas AC, Papageorgiou DG (2000) Neural network methods for boundary value problems with irregular boundaries. IEEE Trans Neural Netw 11:1041–1049
Malek A, Beidokhti SR (2006) Numerical solution for high order deferential equations, using a hybrid neural network—optimization method. Appl Math Comput 183:260–271
Yazid HS, Pakdaman M, Modaghegh H (2011) Unsupervised kernel least mean square algorithm for solving ordinary differential equations. Neurocomputing 74:2062–2071
Selvaraju N, Abdul Samant J (2010) Solution of matrix Riccati differential equation for nonlinear singular system using neural networks. Int J Comput Appl 29:48–54
Shirvany Y, Hayati M, Moradian R (2009) Multilayer perceptron neural networks with novel unsupervised training method for numerical solution of the partial differential equations. Appl Soft Comput 9:20–29
Aartt LP, Van der veer P (2001) Neural network method for solving partial differential equations. Neural Process Lett 14:261–271
He S, Reif K, Unbehauen R (2000) Multilayer neural networks for solving a class of partial differential equations. Neural Netw 13:385–396
Hoda SA, Nagla HA (2011) Neural network methods for mixed boundary value problems. Int J Nonlinear Sci 11:312–316
McFall KS, Mahan JR (2009) Artificial neural network for solution of boundary value problems with exact satisfaction of arbitrary boundary conditions. IEEE Trans Neural Netw 20:1221–1233
Manevitz L, Bitar A, Givoli D (2005) Neural network time series forecasting of finite-element mesh adaptation. Neurocomputing 63:447–463
Leephakpreeda T (2002) Novel determination of differential-equation solutions: universal approximation method. J Comput Appl Math 146:443–457
Mai-Duy N, Tran-Cong T (2001) Numerical solution of differential equations using multi quadric radial basis function networks. Neural Netw 14:185–199
Jianyu L, Siwei L, Yingjian Q, Yaping H (2003) Numerical solution of elliptic partial differential equation using radial basis function neural networks. Neural Netw 16:729–734
Jckiewiez Z, Rahaman M, Welfent BD (2008) Numerical solution of a fredholm integra-differential equation modelling θ-neural networks. Appl Math Comput 195:2523–5363
Tsoulos IG, Lagaris IE (2006) Solving differential equations with genetic programming. Genet Program Evolvable Mach 7:33–54
Parisi DR, Mariani MC, Laborde MA (2003) Solving differential equations with unsupervised neural networks. Chem Eng Process 42:715–721
Mall S, Chakraverty S (2013) Regression based neural network training for the solution of ordinary differential equations. Int J Math Model Numer Optim 4:136–149
Tsoulos IG, Gavrilis D, Glavas E (2009) Solving differential equations with constructed neural networks. Neurocomputing 72:2385–2391
Smaoui N, Al-Enezi S (2004) Modelling the dynamics of nonlinear partial differential equations using neural networks. J Comput Appl Math 170:27–58
Chakraverty S, Singh VP, Sharma RK (2006) Regression based weight generation algorithm in neural network for estimation of frequencies of vibrating plates. J Comput Methods Appl Mech Eng 195:4194–4202
Chakraverty S, Singh VP, Sharma RK, Sharma GK (2009) Modelling vibration frequencies of annular plates by regression based neural network. Appl Soft Comput 9:439–447
Zurada JM (1994) Introduction to artificial neural network. West, Eagan
Haykin S (1999) Neural networks a comprehensive foundation. Prentice Hall, Upper Saddle River
Acknowledgments
The authors are thankful to Department of Science and Technology (DST), Government of India for financial support under Women Scientist Scheme-A.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Chakraverty, S., Mall, S. Regression-based weight generation algorithm in neural network for solution of initial and boundary value problems. Neural Comput & Applic 25, 585–594 (2014). https://doi.org/10.1007/s00521-013-1526-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-013-1526-4