Global learning algorithms for discrete-time cellular neural networks

Two learning algorithms for discrete-time cellular neural networks (DTCNNs) are proposed, which do not require the a priori knowledge of the output trajectory of the network. A cost function is defined, which is minimized by direct search optimization methods and simulated annealing.<<ETX>>

[1]  R. Fletcher.  Practical Methods of Optimization , 1988 .

[2]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[3]  H. Magnussen,et al.  Texture classification, texture segmentation and text segmentation with discrete-time cellular neural networks , 1994, Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).

[4]  Gerhard Seiler.  Grundlagen des Entwurfs zellularer neuronaler Netze , 1993 .

[5]  F. Zou,et al.  A learning algorithm for time-discrete cellular neural networks , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[6]  Josef A. Nossek,et al.  A geometric approach to properties of the discrete-time cellular neural network , 1994 .

[7]  Hubert Harrer.  Discrete time cellular neural networks , 1992, Int. J. Circuit Theory Appl..

[8]  Leon O. Chua,et al.  Genetic algorithm for CNN template learning , 1993 .

[9]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .