Issue No. 07 - July (1994 vol. 16)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.297959
<p>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.</p>
content-addressable storage; neural nets; noise; linear associative memories; generalized inverse; linear models; correlation matrix memory; training noise; S/N ratio gain; auto-associative modes; hetero-associative modes; correlation memory; noise performance
K. Raghunath and V. Cherkassky, "Noise Performance of Linear Associative Memories," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 16, no. , pp. 757-765, 1994.