An analog feedback associative memory

Author

Atiya, Amir ; Abu-Mostafa, Yaser S.

Author_Institution

Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA

Volume

4

Issue

1

fYear

1993

fDate

1/1/1993 12:00:00 AM

Firstpage

117

Lastpage

126

Abstract

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

Keywords

Hopfield neural nets; content-addressable storage; learning (artificial intelligence); Hopfield continuous-time network; analog feedback associative memory; asymptotic stability; hidden layers; learning algorithm; memory vector; neural nets; visible layer; Associative memory; Asymptotic stability; Feedback; Hopfield neural networks; Neural networks; Neurofeedback; Neurons; Pattern recognition; Vector quantization;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.182701

Filename

182701