An analog feedback associative memory
Atiya, A.
Abu-Mostafa, Y.S.
Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA;
This paper appears in: Neural Networks, IEEE Transactions on
Publication Date: Jan 1993
Volume: 4,
Issue: 1
On page(s): 117-126
ISSN: 1045-9227
References Cited: 24
CODEN: ITNNEP
INSPEC Accession Number: 4366022
Digital Object Identifier: 10.1109/72.182701
Current Version Published: 2002-08-06
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
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
