Design and Learning with Cellular Neural Networks

The template coefficients (weights) of a CNN, which d l give a d e s i d p e t f o t " e , can either be found by design OT by learning. .By designw meansl thut the dccrircdfunction to be performed could be translated into a set of local dynamic rules, while "ay ICorning' i s based ezclwively on pairs of input and c o n q w d n g output signals, the nlcrtioMhip of which m y be by far too complicated for the cqlicit fonnulclrion of loml rules. An ov" of design and leaming methods applicrrbk to CNNs, which sometimes att not c M y distingllishcrbk, d l be given k. Both technological constmints imposed by spec$% hadwatt implementation and pmctical constraints caused by the SpCriFc application and q d e m embedding are influencing design and leanzing.

[1]  A. A. Mullin,et al.  Principles of neurodynamics , 1962 .

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

[3]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[4]  Pineda,et al.  Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[5]  S. Agmon.  The Relaxation Method for Linear Inequalities , 1954, Canadian Journal of Mathematics.

[6]  Josef A. Nossek,et al.  Towards a learning algorithm for discrete-time cellular neural networks , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[7]  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).