DocumentCode
2863714
Title
Sparsely symmetric interconnected associative memories
Author
Botoca, Corina
Author_Institution
Telecommun. Dept., Politehnic Inst., Timisoara, Romania
fYear
2000
fDate
2000
Firstpage
113
Lastpage
116
Abstract
This paper presents and theoretically justifies a design procedure for an associative memory, with a cellular neural network structure, using singular values decomposition. By assuring the condition of symmetry of the interconnections, the suggested method generates a completely stable architecture. This guarantees that the obtained neural network never oscillates or becomes chaotic. The performance of the obtained associative memory are presented. The simulation results are compared with other different associative memory designs
Keywords
cellular neural nets; circuit stability; content-addressable storage; singular value decomposition; associative memory; cellular neural network; singular values decomposition; stability; symmetric interconnection; Associative memory; Cellular neural networks; Equations; Feedback; Matrix decomposition; Neural networks; Noise generators; Singular value decomposition; Stability; Symmetric matrices;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Network Applications in Electrical Engineering, 2000. NEUREL 2000. Proceedings of the 5th Seminar on
Conference_Location
Belgrade
Print_ISBN
0-7803-5512-1
Type
conf
DOI
10.1109/NEUREL.2000.902396
Filename
902396
Link To Document