Evolving oscillators in silico

Abstract

We use evolutionary search to automatically find electronic circuits that oscillate, i.e., that periodically toggle an output line from low to high. Reconfigurable hardware in the form of field programable gate arrays (FPGA's)-as opposed to circuit simulation-computes a circuit's fitness which guides the evolutionary search. We find empirically that oscillating circuits can be evolved that closely approximate target frequencies specified a priori. Our evolved oscillators alias a harmonic of the target frequency to satisfy the fitness goal. Frequencies of the evolved oscillators are sensitive to temperature and to the physical piece of silicon in which they operate. Such sensitivities have negative implications for deployment of evolved circuits in conventional applications, but may have positive implications for adaptive computing. We observe that operating the FPGA's transistors at voltages below specification often increases the number and quality of evolved solutions.