Refractory Neuron Circuits

Abstract

Neural networks typically use an abstraction of the behaviour of a biological neuron, in which the continuously varying mean firing rate of the neuron is presumed to carry information about the neuron's time-varying state of excitation. However, the detailed timing of action potentials is known to be important in many biological systems. To build electronic models of such systems, one must have well-characterized neuron circuits that capture the essential behaviour of real neurons in biological systems. In this paper, we describe two simple and compact circuits that fire narrow action potentials with controllable thresholds, pulse widths, and refractory periods. Both circuits are well suited as high-level abstractions of spiking neurons. We have used the first circuit to generate action potentials from a current input, and have used the second circuit to delay and propagate action potentials in an axon delay line. The circuit mechanisms are derived from the behaviour of sodium and potassium conductances in nerve membranes of biological neurons. The first circuit models behaviours at the axon hillock; the second circuit models behaviour at the node of Ranvier in biological neurons. The circuits have been implemented in a 2-micron double-poly CMOS process. Results are presented from working chips.