Adiabatic Spiking Neurons and Synapses for Ultra-Low Energy Neuromorphic Computing

We present an artificial spiking neuron employing capacitive synapses, that is capable of an adiabatic operation and can achieve a cumulative integration of the input spikes. Our transistor-level circuit simulations show that the neuron can exploit both the charging and recovery phases to drive the membrane potential of the neurons and reach 100-150fJ per synaptic operation with a 99.6%-98.8% efficiency of the adiabatic driving at a 40 kHz resonance.