Neuromorphic adaptive control

Abstract

A neuromorphic computing architecture for adaptive control of a class of nonlinear systems is presented. Starting with some prior assumptions about stabilizability of the plants, a stable unsupervised architecture is obtained. It is a parallel distributed architecture, and it is shown that it provides bounded tracking and asymptotic regulation, following a class of teacher models. The feasibility of the method is demonstrated for a robotic manipulator.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>