Neuromorphic Computing: Artificial Neuron and Synapse Realized in an Antiferromagnet/Ferromagnet Heterostructure Using Dynamics of Spin–Orbit Torque Switching (Adv. Mater. 23/2019)

One of the main goals of neuromorphic computing is the implementation and design of systems capable of dynamic evolution with respect to their own experience. In biology, synaptic scaling is the homeostatic mechanism which controls the frequency of neural spikes within stable boundaries for improved learning activity. To introduce such control mechanism in a hardware spiking neural network (SNN), we present here a novel artificial neuron based on phase change memory (PCM) devices capable of internal regulation via homeostatic and plastic phenomena. We experimentally show that this mechanism increases the robustness of the system thus optimizing the multi-pattern learning under spike-timing-dependent plasticity (STDP). It also improves the continual learning capability of hybrid supervised-unsupervised convolutional neural networks (CNNs), in terms of both resilience and accuracy. Furthermore, the use of neurons capable of self-regulating their fire responsivity as a function of the PCM internal state enables the design of dynamic networks. In this scenario, we propose to use the PCM-based neurons to design bio-inspired recurrent networks for autonomous decision making in navigation tasks. The agent relies on neuronal spike-frequency adaptation (SFA) to explore the environment via penalties and rewards. Finally, we show that the conductance drift of the PCM devices, contrarily to the applications in neural network accelerators, can improve the overall energy efficiency of neuromorphic computing by implementing bio-plausible active forgetting.

Download Full-text

Spin-orbit torque–driven propagating spin waves

Science Advances ◽

10.1126/sciadv.aax8467 ◽

2019 ◽

Vol 5 (9) ◽

pp. eaax8467 ◽

Cited By ~ 16

Author(s):

H. Fulara ◽

M. Zahedinejad ◽

R. Khymyn ◽

A. A. Awad ◽

S. Muralidhar ◽

...

Keyword(s):

High Speed ◽

Data Transfer ◽

Dipolar Coupling ◽

Perpendicular Magnetic Anisotropy ◽

Cmos Technology ◽

Spin Orbit ◽

Neuromorphic Computing ◽

Mutual Synchronization ◽

Nonlinear Properties ◽

Highly Nonlinear

Spin-orbit torque (SOT) can drive sustained spin wave (SW) auto-oscillations in a class of emerging microwave devices known as spin Hall nano-oscillators (SHNOs), which have highly nonlinear properties governing robust mutual synchronization at frequencies directly amenable to high-speed neuromorphic computing. However, all demonstrations have relied on localized SW modes interacting through dipolar coupling and/or direct exchange. As nanomagnonics requires propagating SWs for data transfer and additional computational functionality can be achieved using SW interference, SOT-driven propagating SWs would be highly advantageous. Here, we demonstrate how perpendicular magnetic anisotropy can raise the frequency of SOT-driven auto-oscillations in magnetic nanoconstrictions well above the SW gap, resulting in the efficient generation of field and current tunable propagating SWs. Our demonstration greatly extends the functionality and design freedom of SHNOs, enabling long-range SOT-driven SW propagation for nanomagnonics, SW logic, and neuromorphic computing, directly compatible with CMOS technology.

Download Full-text