Towards a learning algorithm for discrete-time cellular neural networks
H. Magnussen, Josef A. Nossek · 2003
The learning process for a discrete-time cellular network is formulated as an optimization problem. This involves minimizing an objective function, which is a measure of the errors in the desired input-to-output image mapping process performed by the network. With this approach, the learning algorithm finds the trajectories, so they no longer have to be designed by the user.>