Based on the experiment, we extend the concept to a three-terminal device structure that can be easily interfaced with CMOS peripherals for enabling different genres of unconventional computing scenarios. This work firstly attempts to experimentally validate prior theoretical proposals for utilizing spin-orbit torque switching nanomagnets as biased random number generators where the bias can be tuned using the magnitude of the input stimulus by operating the magnets in the stochastic regime 12, 13, 14, 15, 16. While such spin-orbit torque induced magnetization switching has been extensively studied in the deterministic regime, it is intrinsically probabilistic due to the inherent time-varying thermal noise involved in the magnetization dynamics. Recent proposals have also explored deterministic switching in perpendicular magnets without the assistance of any external field 9, 10, 11. While magnets with in-plane anisotropy can be switched directly by spin-orbit torque (SOT), perpendicular magnets require an external magnetic field for deterministic switching. Nanomagnet switching due to input charge current flowing through the heavy-metal (HM) underlayer is mainly attributed to spin-Hall effect (SHE) 8, wherein, a transverse spin current is injected in the nanomagnet lying on top. Spin-orbit torque generated by an underlying heavy metal has recently emerged as an energy-efficient mechanism for magnetization reversal 1, 2, 3 and domain wall motion 4, 5, 6, 7. ![]() This work can potentially pave the way for hardware that directly mimics the computational units of Bayesian inference. We show that the probabilistic switching of Ta/CoFeB/MgO heterostructures in presence of spin-orbit torque and thermal noise can be harnessed to enable probabilistic inference in a plethora of unconventional computing scenarios. In this work, we experimentally demonstrate a spintronic device that offers a direct mapping to the functionality of such a controllable stochastic switching element. In tune with such observations, neuromorphic and other unconventional computing platforms have recently started adopting the usage of computational units that generate outputs probabilistically, depending on the magnitude of the input stimulus. ![]() As a matter of fact, preliminary research has revealed that stochastic functionalities also underlie the spiking behavior of neurons in cortical microcircuits of the human brain. Probabilistic inference from real-time input data is becoming increasingly popular and may be one of the potential pathways at enabling cognitive intelligence.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |