Back-Propagation Learning of Partial Functional Differential Equation with Discrete Time Delay

• Published in: Artificial Intelligence: Methodology, Systems, and Applications pp. 186 - 193
• Main Authors: Kmet, Tibor, Kmetova, Maria
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing 2014
• Series: Lecture Notes in Computer Science
• Subjects: feed-forward neural network; multilayer Hopfield neural network with a discrete time delay and diffusion-reaction term; numerical solution; prey-predator system with a discrete time delay and diffusion-reaction term; time-dependent learning
• ISBN: 9783319105536; 3319105531
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-10554-3_18

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.