Abstract
Spiking neural networks, inspired by biological neural systems, could process immense volumes of spatio-temporal data by representing them as spikes. Here, we propose to implement compact, scalable, energy-efficient spiking neurons based on the unique insulator-metal transition in Vanadium dioxide <tex>$(VO_{2})$</tex> which interact through memristive synapses, to emulate a Liquid State Machine (LSM). Further, we demonstrate the implementation of this recurrent neural network as a temporal auto-encoder, and adaptive channel equalizer for application in neuromorphic signal processing. Our approach provides a pathway to reduce component count <tex>$(50\ -100X)$</tex> and improve energy efficiency <tex>$(> 50X)$</tex> over conventional CMOS based implementations.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
