TY - JOUR
T1 - Hybrid Spintronic-CMOS Spiking Neural Network with On-Chip Learning
T2 - Devices, Circuits, and Systems
AU - Sengupta, Abhronil
AU - Banerjee, Aparajita
AU - Roy, Kaushik
N1 - Publisher Copyright:
© 2016 American Physical Society.
PY - 2016/12/8
Y1 - 2016/12/8
N2 - Over the past decade, spiking neural networks (SNNs) have emerged as one of the popular architectures to emulate the brain. In SNNs, information is temporally encoded and communication between neurons is accomplished by means of spikes. In such networks, spike-timing-dependent plasticity mechanisms require the online programing of synapses based on the temporal information of spikes transmitted by spiking neurons. In this work, we propose a spintronic synapse with decoupled spike-transmission and programing-current paths. The spintronic synapse consists of a ferromagnet-heavy-metal heterostructure where the programing current through the heavy metal generates spin-orbit torque to modulate the device conductance. Low programing energy and fast programing times demonstrate the efficacy of the proposed device as a nanoelectronic synapse. We perform a simulation study based on an experimentally benchmarked device-simulation framework to demonstrate the interfacing of such spintronic synapses with CMOS neurons and learning circuits operating in the transistor subthreshold region to form a network of spiking neurons that can be utilized for pattern-recognition problems.
AB - Over the past decade, spiking neural networks (SNNs) have emerged as one of the popular architectures to emulate the brain. In SNNs, information is temporally encoded and communication between neurons is accomplished by means of spikes. In such networks, spike-timing-dependent plasticity mechanisms require the online programing of synapses based on the temporal information of spikes transmitted by spiking neurons. In this work, we propose a spintronic synapse with decoupled spike-transmission and programing-current paths. The spintronic synapse consists of a ferromagnet-heavy-metal heterostructure where the programing current through the heavy metal generates spin-orbit torque to modulate the device conductance. Low programing energy and fast programing times demonstrate the efficacy of the proposed device as a nanoelectronic synapse. We perform a simulation study based on an experimentally benchmarked device-simulation framework to demonstrate the interfacing of such spintronic synapses with CMOS neurons and learning circuits operating in the transistor subthreshold region to form a network of spiking neurons that can be utilized for pattern-recognition problems.
UR - http://www.scopus.com/inward/record.url?scp=85010452322&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85010452322&partnerID=8YFLogxK
U2 - 10.1103/PhysRevApplied.6.064003
DO - 10.1103/PhysRevApplied.6.064003
M3 - Article
AN - SCOPUS:85010452322
SN - 2331-7019
VL - 6
JO - Physical Review Applied
JF - Physical Review Applied
IS - 6
M1 - 064003
ER -