Title :
Cellular neural networks for associative memories
Author :
Liu, Derong ; Michel, Anthony N.
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
fDate :
2/1/1993 12:00:00 AM
Abstract :
A synthesis procedure for designing nonsymmetric cellular neural networks (CNN) with a predetermined local interconnection structure that will store a set of desired bipolar vectors as memory points is presented. A specific case of constructing Chinese characters is presented to demonstrate the applicability of the results. Simulation results show that all the vectors corresponding to 50 commonly used Chinese characters are reachable memory vectors of the synthesized CNN
Keywords :
cellular arrays; character recognition; character sets; content-addressable storage; neural nets; Chinese characters; associative memories; bipolar vectors storage; character construction; local interconnection structure; nonsymmetric cellular neural networks; synthesis procedure; Associative memory; Cellular neural networks; Circuit synthesis; Eigenvalues and eigenfunctions; Equations; Image processing; Network synthesis; Neural networks; Signal synthesis; Very large scale integration;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on
