Title :
Capacity of cellular neural networks as associative memories
Author :
Lukianiuk, Andrzej
Author_Institution :
Inst. of Control & Ind. Electron., Warsaw Univ. of Technol., Poland
Abstract :
In the paper a cellular neural network (CNN) architecture as an associative memory is considered. The boundary for the maximum number of memory vectors is obtained. The result suggests that the maximum number of memory vectors arbitrarily chosen from a set of linearly independent vectors is not related to the size of CNN but depends only on radius of the neighborhood
Keywords :
cellular neural nets; content-addressable storage; neural net architecture; associative memories; cellular neural networks; linearly independent vectors; memory vectors; Associative memory; Cellular neural networks; Design methodology; Equations; Hopfield neural networks; Industrial electronics; Memory architecture; Network synthesis; Neural networks; Neurons;
Conference_Titel :
Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on
Conference_Location :
Seville
Print_ISBN :
0-7803-3261-X
DOI :
10.1109/CNNA.1996.566486
