Neural network architecture for crossbar switch control

Author

Troudet, Terry P. ; Walters, Stephen M.

Author_Institution

Bell Commun. Res., Red Bank, NJ, USA

Volume

38

Issue

1

fYear

1991

fDate

1/1/1991 12:00:00 AM

Firstpage

42

Lastpage

56

Abstract

A Hopfield neural network architecture for the real-time control of a crossbar switch for switching pockets at maximum throughput is proposed. The network performance and processing time are derived from a numerical simulation of the transitions of the neural network. A method is proposed to optimize electronic component parameters and synaptic connections, and it is fully illustrated by the computer simulation of a VLSI implementation of 4×4 neural net controller. The extension to larger size crossbars is demonstrated through the simulation of an 8×8 crossbar switch controller, where the performance of the neural computation is discussed in relation to electronic noise and inhomogeneities of network components

Keywords

VLSI; electronic switching systems; neural nets; packet switching; parallel architectures; real-time systems; Hopfield neural network architecture; VLSI implementation; crossbar switch control; network performance; neural net controller; numerical simulation; processing time; real-time control; synaptic connections; telecommunication control; Computational modeling; Computer simulation; Electronic components; Hopfield neural networks; Neural networks; Numerical simulation; Optimization methods; Switches; Throughput; Very large scale integration;

fLanguage

English

Journal_Title

Circuits and Systems, IEEE Transactions on

Publisher

ieee

ISSN

0098-4094

Type

jour

DOI

10.1109/31.101302

Filename

101302