Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published July 1987 | Published
Journal Article Open

The capacity of the Hopfield associative memory

Abstract

Techniques from coding theory are applied to study rigorously the capacity of the Hopfield associative memory. Such a memory stores n-tuple of ±1's. The components change depending on a hard-limited version of linear functions of all other components. With symmetric connections between components, a stable state is ultimately reached. By building up the connection matrix as a sum-of-outer products of m fundamental memories, one hopes to be able to recover a certain one of the m memories by using an initial n-tuple probe vector less than a Hamming distance n/2 away from the fundamental memory. If m fundamental memories are chosen at random, the maximum asymptotic value of min order that most of the m original memories are exactly recoverable is n/(2 log n). With the added restriction that every one of the m fundamental memories be recoverable exactly, m can be no more than n/(4 log n)asymptotically as n approaches infinity. Extensions are also considered, in particular to capacity under quantization of the outer-product connection matrix. This quantized memory capacity problem is closely related to the capacity of the quantized Gaussian channel.

Additional Information

© 1987 IEEE. Reprinted with permission. Manuscript deceived February 3, 1986; revised October 28, 1986. This work was supported in part by the National Aeronautics and Space Administration through the Jet Propulsion Laboratory of the California Institute of Technology and in part by the Defense Advanced Research Projects Agency. This work was partially presented at ISIT 85, Brighton, England, June 1985. We thank A. Dembo for pointing out an error in a previous version of this paper.

Attached Files

Published - MCEieeetit87.pdf

Files

MCEieeetit87.pdf
Files (3.4 MB)
Name Size Download all
md5:460ca8c9f6e3785a692ada39a69d838a
3.4 MB Preview Download

Additional details

Created:
August 22, 2023
Modified:
October 23, 2023