Noise facilitation in associative memories of exponential capacity

Recent advances in associative memory design through structured pattern sets and graph-based inference al- gorithms have allowed reliable learning and recall of an exponential number of patterns. Although these designs correct external errors in recall, they assume neurons that compute noiselessly, in contrast to the highly variable neurons in brain regions thought to operate associatively such as hippocampus and olfactory cortex. Here we consider associative memories with noisy internal computations and analytically characterize performance. As long as the internal noise level is below a specified threshold, the error probability in the recall phase can be made exceedingly small. More surprisingly, we show that internal noise actually improves the performance of the recall phase while the pattern retrieval capacity remains intact, i.e., the number of stored patterns does not reduce with noise (up to a threshold). Computational experiments lend additional support to our theoretical analysis. This work suggests a functional benefit to noisy neurons in biological neuronal networks.

Published in:
Journal of Neural Computation, 26, 11, 2493-2526
Cambridge, Mit Press
The simulation code for this paper is available at the

Note: The status of this file is: Anyone

 Record created 2014-06-09, last modified 2020-05-19

Publisher's version:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
(Not yet reviewed)