Abstract
The present paper describes the back-propagation learning of a partial functional differential equation with reaction-diffusion term. The time-dependent recurrent learning algorithm is developed for a delayed recurrent neural network with the reaction-diffusion term. The proposed simulation methods are illustrated by the back-propagation learning of continuous multilayer Hopfield neural network with a discrete time delay and reaction-diffusion term using the prey-predator system as a teacher signal. The results show that the continuous Hopfield neural networks are able to approximate the signals generated from the predator-prey system with Hopf bifurcation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Becerikli, Y., Konar, A.F., Samad, T.: Inteligent optimal control with dynamic neural networks. Neural Network 16, 251–259 (2003)
Farmer, J.D.: Chaotic Attractors of an infinite-dimensional dynamic system. Physica 4D, 366–393 (1982)
Hornik, M., Stichcombe, M., White, H.: Multilayer feed forward networks are universal approximators. Neural Networks 3, 256–366 (1989)
Jana, S., Chakraborty, M., Chakraborty, K., Kar, T.K.: Global stability and bifurcation of time delayed prey-predator system incorporating prey refuge. Mathematics and Computers in Simulation 85, 57–77 (2012)
Kmet, T., Kmetova, M.: Adaptive Critic Neural Network Solution of Optimal Control Problems with Discrete Time Delays. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 483–494. Springer, Heidelberg (2013)
Morton, K.W.: Numerical solution of Convection-Diffusion Problems. Chapman - Hall, London (1996)
Polak, E.: Optimization Algorithms and Consistent Approximation. Springer, New York (1997)
Rumelhart, D.F., Hinton, G.E., Wiliams, R.J.: Learning internal representation by error propagation. In: Rumelhart, D.E., McClelland, D.E., PDP Research Group (eds.) Parallel Distributed Processing: Foundation, vol. 1, pp. 318–362. The MIT Press, Cambridge (1987)
Sandberg, E.W.: Notes on uniform approximation of time-varying systems on finite time intervals. IEEE Transactions on Circuits and Systems-1: Fundamental Theory and Applications 45(8), 305–325 (1998)
Tokuda, I., Hirai, Y., Tokunaga, R.: Back-propagation learning of infinite-dimensional dynamical system. In: Proceedings of 1993 International Conference on Neural Network, pp. 2271–2275 (1993)
Tokuda, I., Tokunaga, R., Aihara, K.: Back-propagation learning of infinite-dimensional dynamical systems. Neural Networks 16, 1179–1193 (2003)
Werbos, P.J.: Approximate dynamic programming for real-time control and neural modelling. In: White, D.A., Sofge, D.A. (eds.) Handbook of Intelligent Control: Neural Fuzzy, and Adaptive Approaches, pp. 493–525. Van Nostrand Reinhold, New York (1992)
Wu, J.: Theory and Applications of Partial Functional Differential Equations. Applied Math. Sciences, vol. 119. Springer, New York (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kmet, T., Kmetova, M. (2014). Back-Propagation Learning of Partial Functional Differential Equation with Discrete Time Delay. In: Agre, G., Hitzler, P., Krisnadhi, A.A., Kuznetsov, S.O. (eds) Artificial Intelligence: Methodology, Systems, and Applications. AIMSA 2014. Lecture Notes in Computer Science(), vol 8722. Springer, Cham. https://doi.org/10.1007/978-3-319-10554-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-10554-3_18
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10553-6
Online ISBN: 978-3-319-10554-3
eBook Packages: Computer ScienceComputer Science (R0)