A Caltech Library Service

An analog feedback associative memory

Atiya, Amir and Abu-Mostafa, Yaser S. (1993) An analog feedback associative memory. IEEE Transactions on Neural Networks, 4 (1). pp. 117-126. ISSN 1045-9227.

See Usage Policy.


Use this Persistent URL to link to this item:


A method for the storage of analog vectors, i.e., vectors whose components are real-valued, is developed for the Hopfield continuous-time network. An important requirement is that each memory vector has to be an asymptotically stable (i.e. attractive) equilibrium of the network. Some of the limitations imposed by the continuous Hopfield model on the set of vectors that can be stored are pointed out. These limitations can be relieved by choosing a network containing visible as well as hidden units. An architecture consisting of several hidden layers and a visible layer, connected in a circular fashion, is considered. It is proved that the two-layer case is guaranteed to store any number of given analog vectors provided their number does not exceed 1 + the number of neurons in the hidden layer. A learning algorithm that correctly adjusts the locations of the equilibria and guarantees their asymptotic stability is developed. Simulation results confirm the effectiveness of the approach.

Item Type:Article
Related URLs:
URLURL TypeDescription
Additional Information:© 1993 IEEE. Reprinted with permission. Manuscript received August 24, 1990; revised August 1, 1992. This work was supported by the Office of Naval Research under Grant N00014-89-J-1062.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00014-89-J-1062
Issue or Number:1
Record Number:CaltechAUTHORS:ATIieeetnn93
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:2961
Deposited By: Archive Administrator
Deposited On:08 May 2006
Last Modified:02 Oct 2019 22:58

Repository Staff Only: item control page