Noise performance of linear associative memories

Author

Raghunath, Kalavai J. ; Cherkassky, Vladimir

Author_Institution

Dept. of Electr. Eng., Minnesota Univ., Minneapolis, MN, USA

Volume

16

Issue

7

fYear

1994

fDate

7/1/1994 12:00:00 AM

Firstpage

757

Lastpage

765

Abstract

The performance of two commonly used linear models of associative memories, generalized inverse (GI) and correlation matrix memory (CMM) is studied analytically in the presence of a new type of noise (training noise due to noisy training patterns). Theoretical expressions are determined for the S/N ratio gain of the GI and CMM memories in the auto-associative and hetero-associative modes of operation. It is found that the GI method performance degrades significantly in the presence of training noise while the CMM method is relatively unaffected by it. The 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

content-addressable storage; neural nets; noise; S/N ratio gain; auto-associative modes; correlation matrix memory; correlation memory; generalized inverse; hetero-associative modes; linear associative memories; linear models; noise performance; training noise; Associative memory; Coordinate measuring machines; Crosstalk; Degradation; Encoding; Multi-layer neural network; Neural networks; Pattern analysis; Performance analysis; Signal to noise ratio;

fLanguage

English

Journal_Title

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Publisher

ieee

ISSN

0162-8828

Type

jour

DOI

10.1109/34.297959

Filename

297959