Hybrid spin‐CMOS stochastic spiking neuron for high‐speed emulation of In vivo neuron dynamics

The spintronic stochastic spiking neuron (S3N) developed herein realises biologically mimeticstochastic spiking characteristics observed within in vivo cortical neurons,while operating several orders of magnitude more rapidly and exhibiting afavourable energy profile. This work leverages a novel probabilistic spintronicswitching element device that provides thermally‐driven and current‐controlledtunable stochasticity in a compact, low‐energy, and high‐speed package. In orderto close the loop, the authors utilise a second‐order complementarymetal‐oxide‐semiconductor (CMOS) synapse with variable weight control thataccumulates incoming spikes into second‐order transient current signals, whichresemble the excitatory post‐synaptic potentials found in biological neurons,and can be used to drive post‐synaptic S3Ns. Simulation program with integratedcircuit emphasis (SPICE) simulation results indicate that the equivalent of 1 sof in vivo neuronal spiking characteristics can be generated on the order ofnanoseconds, enabling the feasibility of extremely rapid emulation of in vivoneuronal behaviours for future statistical models of cortical informationprocessing. Their results also indicate that the S3N can generate spikes on theorder of ten picoseconds while dissipating only 0.6–9.6 μW, depending on thespiking rate. Additionally, they demonstrate that an S3N can implementperceptron functionality, such as AND‐gate‐ and OR‐gate‐based logic processing,and provide future extensions of the work to more advanced stochasticneuromorphic architectures.