A neural network to design neural networks

Author

Perfetti, R.

Author_Institution

INFO-COM Dept., Rome Univ., Italy

Volume

38

Issue

9

fYear

1991

fDate

9/1/1991 12:00:00 AM

Firstpage

1099

Lastpage

1103

Abstract

The design of the Hopfield associative memory is reformulated in terms of a constraint satisfaction problem. An electronic neural net capable of solving this problem in real time is proposed. Circuit solutions correspond to symmetrical zero-diagonal matrices that possess few spurious stable states. The stability of the net is proved using a suitable Lyapunov function, and simulation results are presented. The proposed network also permits design of an associative memory with a given set of state transitions, avoiding the computation of pseudo-inverses. The net exhibits several features that make it attractive for VLSI implementation

Keywords

Lyapunov methods; VLSI; content-addressable storage; matrix algebra; neural nets; real-time systems; stability; Hopfield associative memory; Lyapunov function; VLSI implementation; constraint satisfaction problem; electronic neural net; neural network design; real time; stability; state transitions; symmetrical zero-diagonal matrices; Associative memory; Circuit simulation; Circuit stability; Computational modeling; Computer networks; Linear programming; Lyapunov method; Neural networks; Symmetric matrices; Very large scale integration;

fLanguage

English

Journal_Title

Circuits and Systems, IEEE Transactions on

Publisher

ieee

ISSN

0098-4094

Type

jour

DOI

10.1109/31.83884

Filename

83884