Switching Dynamics in Vanadium Dioxide-Based Stochastic Thermal Neurons

We report on switching dynamics of individual and coupled vanadium dioxide (VO₂) devices subject to voltage pulses as the temperature is systematically varied from room temperature spanning the insulator–metal transition (IMT) temperature. The switching voltage of single devices has a strong relationship with both temperature and voltage pulsewidth. Two-step switching in connected VO₂ devices has been noted in current transient plots and was found to depend on temperature, pulsewidth, and pulse amplitude. Experimental switching behavior measured from VO₂ artificial neurons was implemented into a spiking neural network (SNN). During training, modulating the switching voltage via temperature affords a novel method to implement homeostasis with the coupled devices. Simulation results show the efficacy of the stochastic neuronal characteristics and the proposed homeostasis mechanism on a standard digit recognition task. These studies contribute to ongoing efforts in neuromorphic computing exploiting collective phase transitions.