Title :
Towards a learning algorithm for discrete-time cellular neural networks
Author :
Magnussen, Holger ; Nossek, Josef A.
Author_Institution :
Inst. for Network Theory & Circuit Design, Tech. Univ. of Munich, Germany
Abstract :
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
Keywords :
image recognition; learning (artificial intelligence); neural nets; optimisation; discrete-time cellular neural networks; input-to-output image mapping; learning algorithm; objective function; optimization; Cellular networks; Cellular neural networks; Circuit synthesis; Clocks; Cyclic redundancy check; Hamming distance; Image converters; Monitoring; Pain; Tiles;
Conference_Titel :
Cellular Neural Networks and their Applications, 1992. CNNA-92 Proceedings., Second International Workshop on
Conference_Location :
Munich
Print_ISBN :
0-7803-0875-1
DOI :
10.1109/CNNA.1992.274351
