Architectures for analog VLSI implementation of neural networks for solving linear equations with inequality constraints

2 January 2003

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. 3, 1529-1532
https://doi.org/10.1109/iscas.1992.230208

Abstract

A novel algorithm for solving generalized systems of linear equations subject to linear inequalities is proposed. The algorithm is robust with respect to wild (spiky) noise and outliers. The algorithm is expressed completely in differential equations. An OTA (operational transconductance amplifier)-based implementation of the algorithm as an analog VLSI circuit in CMOS technology is discussed. One of the many possible applications of the proposed techniques is the implementation of cellular neural networks with real-time on-chip learning capabilities.

Keywords

This publication has 7 references indexed in Scilit:

Neural networks for solving systems of linear equations and related problems
IEEE Transactions on Circuits and Systems I: Regular Papers, 1992
Extended transconductance adjustment/linearisation technique
Electronics Letters, 1991
Design method for cellular neural network with linear relaxation
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1991
Operational transconductance amplifier-based nonlinear function syntheses
IEEE Journal of Solid-State Circuits, 1989
MOS Switched-Capacitor and Continuous-Time Integrated Circuits and Systems
Published by Springer Nature ,1989
Cellular neural networks: theory
IEEE Transactions on Circuits and Systems, 1988
Neural networks and physical systems with emergent collective computational abilities.
Proceedings of the National Academy of Sciences, 1982