Noise Performance of Linear Associative Memories

Kalavai J. Raghunath, Vladimir Cherkassky

Research output: Contribution to journalArticle

3 Scopus citations

Abstract

The performance of two commonly used linear models of associative memories, generalized inverse (G1) 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 SNR (signal-to-noise 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.

Original languageEnglish (US)
Pages (from-to)757-765
Number of pages9
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume16
Issue number7
DOIs
StatePublished - Jul 1994

Keywords

  • Associative memory
  • correlation memory matrix
  • generalized inverse
  • noise performance

Fingerprint Dive into the research topics of 'Noise Performance of Linear Associative Memories'. Together they form a unique fingerprint.

  • Cite this