Title :
Analysis of the noise performance of associative memories
Author :
Raghunath, Kalavai J. ; Cherkassky, Vladimir
Author_Institution :
Dept. of Electr. Eng., Minnesota Univ., Minneapolis, MN, USA
Abstract :
The performances of two commonly used associative memories, generalized inverse (GI) and correlation memory matrix (CMM), are studied analytically and compared. The effects of crosstalk and a novel type of noise (memory noise appearing due to noisy training patterns) are also considered. Theoretical expressions are determined for the SNR (signal to noise ratio) gain of the GI and CMM memories in the auto-associative and heteroassociative modes of operation. It is found that the GI method performance degrades significantly in the presence of memory noise, while the CMM method is relatively unaffected. In overall performance, the GI method is superior to that of the CMM method, except at high values of input stimulus noise, or when the number of associations stored is close to the dimension of the key vectors. Theoretical expressions are plotted and compared with the results obtained from Monte Carlo simulations, and the two are found to be in excellent agreement
Keywords :
Monte Carlo methods; content-addressable storage; crosstalk; learning (artificial intelligence); neural nets; Monte Carlo simulations; associative memories; autoassociative mode; correlation memory matrix; crosstalk; generalized inverse; heteroassociative modes; noise; noise performance; noisy training patterns; signal to noise ratio; Analytical models; Associative memory; Coordinate measuring machines; Crosstalk; Degradation; Pattern recognition; Performance analysis; Signal to noise ratio; Vectors;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227010
