Search

The development of an efficient neuromorphic computing system requires the use of nanodevices that intrinsically emulate the biological behavior of neurons and synapses. While numerous artificial synapses have been shown to store weights in a manner analogous to biological synapses, the challenge of developing an artificial neuron is impeded by the necessity to include leaking, integrating, firing, and lateral inhibition features. In particular, previous proposals for artificial neurons have required the use of external circuits to perform lateral inhibition, thereby decreasing the efficiency of the resulting neuromorphic computing system. This work therefore proposes a leaky integrate-and-fire neuron that intrinsically provides lateral inhibition, without requiring any additional circuitry. The proposed neuron is based on the previously proposed domain-wall magnetic tunnel junction devices, which have been proposed as artificial synapses and experimentally demonstrated for non-volatile logic. Single-neuron micromagnetic simulations are provided that demonstrate the ability of this neuron to implement the required leaking, integrating, and firing. These simulations are then extended to pairs of adjacent neurons to demonstrate, for the first time, lateral inhibition between neighboring artificial neurons. Finally, this intrinsic lateral inhibition is applied to a ten-neuron crossbar structure and trained to identify handwritten digits and shown via direct large-scale micromagnetic simulation for 100 digits to correctly identify the proper signal for 94% of the digits. [ABSTRACT FROM AUTHOR]

CMOS devices display volatile characteristics and are not well suited for analog applications such as neuromorphic computing. Spintronic devices, on the other hand, exhibit both non-volatile and analog features, which are well suited to neuromorphic computing. Consequently, these novel devices are at the forefront of beyond-CMOS artificial intelligence applications. However, a large quantity of these artificial neuromorphic devices still require the use of CMOS to implement various neuromorphic functionalities, which decreases the efficiency of the system. To resolve this, we have previously proposed a number of artificial neurons and synapses that do not require CMOS for operation. Although these devices are a significant improvement over previous renditions, their ability to enable neural network learning and recognition is limited by their intrinsic activation functions. This work proposes modifications to these spintronic neurons that enable configuration of the activation functions through control of the shape of a magnetic domain wall track. Linear and sigmoidal activation functions are demonstrated in this work, which can be extended through a similar approach to enable a wide variety of activation functions. [ABSTRACT FROM AUTHOR]

Due to their nonvolatility and intrinsic current integration capabilities, spintronic devices that rely on domain wall (DW) motion through a free ferromagnetic track have garnered significant interest in the field of neuromorphic computing. Although a number of such devices have already been proposed, they require the use of external circuitry to implement several important neuronal behaviors. As such, they are likely to result in either a decrease in energy efficiency, an increase in fabrication complexity, or even both. To resolve this issue, we have proposed three individual neurons that are capable of performing these functionalities without the use of any external circuitry. To implement leaking, the first neuron uses a dipolar coupling field, the second uses an anisotropy gradient and the third uses shape variations of the DW track. [ABSTRACT FROM AUTHOR]

Spintronic devices based on domain wall (DW) motion through ferromagnetic nanowire tracks have received great interest as components of neuromorphic information processing systems. Previous proposals for spintronic artificial neurons required external stimuli to perform the leaking functionality, one of the three fundamental functions of a leaky integrate-and-fire (LIF) neuron. The use of this external magnetic field or electrical current stimulus results in either a decrease in energy efficiency or an increase in fabrication complexity. In this article, we modify the shape of previously demonstrated three-terminal magnetic tunnel junction neurons to perform the leaking operation without any external stimuli. The trapezoidal structure causes a shape-based DW drift, thus intrinsically providing the leaking functionality with no hardware cost. This LIF neuron, therefore, promises to advance the development of spintronic neural network crossbar arrays. [ABSTRACT FROM AUTHOR]

The spin-transfer torque domain wall (DW) magnetic tunnel junction (MTJ) enables spintronic logic circuits that can be directly cascaded without deleterious signal conversion circuitry and is one of the only spintronic devices for which cascading has been demonstrated experimentally. However, experimental progress has been impeded by a cumbersome modeling technique that requires a combination of micromagnetic and SPICE simulations. This paper, therefore, presents a SPICE-only device model that efficiently determines the DW motion resulting from spin accumulation and calculates the corresponding MTJ resistance. This model has been validated through comparison to the authoritative micromagnetic-based model, enabling reliable prediction of circuit behavior as a function of device parameters with a 10 000 $\times $ reduction in the simulation time. This model thus enables deeper device and circuit investigation, advancing the prospects for nonvolatile spintronic computing systems that overcome the von Neumann bottleneck. [ABSTRACT FROM AUTHOR]