Neural Spiking Dynamics in Asynchronous Digital Circuits
The authors implement a digital neuron in silicon using delay-insensitive asynchronous circuits. Their design numerically solves the Izhikevich equations with a fixed-point number representation, resulting in a compact and energy-efficient neuron with a variety of dynamical characteristics. A digital implementation results in stable, reliable and highly programmable circuits, while an asynchronous design style leads to energy-efficient clock-less neurons and their networks that mimic the event-driven nature of biological nervous systems. In 65 nm CMOS technology at 1 V operating voltage and a 16-bit word length, their neuron can update its state 11,600 times per millisecond while consuming 0.5 nJ per update.