A three-neuron controller. I

This is the first in a sequence of papers which discuss the biological plausibility of a neural control circuit consisting of two input neurons and one output neuron. An implementation of this circuit has been shown to control a simple first order linear control system on a par with a fuzzy controller designed for the same process (Alexander, 1994). The neural circuit successfully maintained the height of water in a tank under conditions of varying input flow. In this paper, the author discusses the equations used in the simple neural circuit; the simple neural circuit's method of controlling first order linear systems; demonstrates the three-neuron controller's capability to solve the truck backer-upper problem; and discusses the applicability of the three-neuron controller (TNC) in harder problems. The author also discusses a generalized software package (FuzComp) that is being developed to assist in the author's studies.