Title :
Sparsely symmetric interconnected associative memories
Author_Institution :
Telecommun. Dept., Politehnic Inst., Timisoara, Romania
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;
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
DOI :
10.1109/NEUREL.2000.902396
