Stochastic spin-orbit-torque device as the STDP synapse for spiking neural networks
arXiv:2304.08856 · doi:10.1007/s11433-022-2081-5
Abstract
Neuromorphic hardware as a non-Von Neumann architecture has better energy efficiency and parallelism than the conventional computer. Here, with numerical modeling spin-orbit torque (SOT) device using current-induced SOT and Joule heating effects, we acquire its magnetization switching probability as a function of the input current pulses and use it to mimic the spike-timing-dependent plasticity learning behavior like actual brain working. We further demonstrate that the artificial spiking neural network (SNN) built by this SOT device can perform unsupervised handwritten digit recognition with the accuracy of 80% and logic operation learning. Our work provides a new clue to achieving SNN-based neuromorphic hardware using high-energy efficiency and nonvolatile spintronics nanodevices
arXiv comment8 pages, 5 figures
References in corpus (11)
- The design and verification of Mumax3
- Spin torque building blocks
- Quantitative characterization of the spin orbit torque using harmonic Hall voltage measurements
- Current induced torques and interfacial spin-orbit coupling: Semiclassical Modeling
- Ultrafast magnetization switching by spin-orbit torques
- Threshold current for switching of a perpendicular magnetic layer induced by spin Hall effect
- Thermally-Activated Magnetic Reversal Induced by a Spin-Polarized Current
- Physical reservoir computing built by spintronic devices for temporal information processing
- Adaptively time stepping the stochastic Landau-Lifshitz-Gilbert equation at nonzero temperature: implementation and validation in MuMax3
- Thermally activated switching of perpendicular magnet by spin-orbit spin torque
- Thermally assisted spin transfer torque switching in synthetic free layers