skip to main content

Title: Lateral inhibition in magnetic domain wall racetrack arrays for neuromorphic computing
Neuromorphic computing captures the quintessential neural behaviors of the brain and is a promising candidate for the beyond-von Neumann computer architectures, featuring low power consumption and high parallelism. The neuronal lateral inhibition feature, closely associated with the biological receptive eld, is crucial to neuronal competition in the nervous system as well as its neuromorphic hardware counterpart. The domain wall - magnetic tunnel junction (DW-MTJ) neuron is an emerging spintronic arti cial neuron device exhibiting intrinsic lateral inhibition. This work discusses lateral inhibition mechanism of the DW-MTJ neuron and shows by micromagnetic simulation that lateral inhibition is eciently enhanced by the Dzyaloshinskii-Moriya interaction (DMI).
Authors:
; ; ; ; ; ;
Editors:
Drouhin, Henri-Jean M.; Wegrowe, Jean-Eric; Razeghi, Manijeh
Award ID(s):
1940788 1910800
Publication Date:
NSF-PAR ID:
10212813
Journal Name:
Proc. SPIE, Spintronics XIII
Volume:
11470
Issue:
1147011-1
Sponsoring Org:
National Science Foundation
More Like this
  1. The challenge of developing an efficient artificial neuron is impeded by the use of external CMOS circuits to perform leaking and lateral inhibition. The proposed leaky integrate-and-fire neuron based on the three terminal magnetic tunnel junction (3T-MTJ) performs integration by pushing its domain wall (DW) with spin-transfer or spin-orbit torque. The leaking capability is achieved by pushing the neurons’ DWs in the direction opposite of integration using a stray field from a hard ferromagnet or a non-uniform energy landscape resulting from shape or anisotropy variation. Firing is performed by the MTJ stack. Finally, analog lateral inhibition is achieved by dipolar field repulsive coupling from each neuron. An integrating neuron thus pushes slower neighboring neurons’ DWs in the direction opposite of integration. Applying this lateral inhibition to a ten-neuron output layer within a neuromorphic crossbar structure enables the identification of handwritten digits with 94% accuracy.
  2. In biological brains, recurrent connections play a crucial role in cortical computation, modulation of network dynamics, and communication. However, in recurrent spiking neural networks (SNNs), recurrence is mostly constructed by random connections. How excitatory and inhibitory recurrent connections affect network responses and what kinds of connectivity benefit learning performance is still obscure. In this work, we propose a novel recurrent structure called the Laterally-Inhibited Self-Recurrent Unit (LISR), which consists of one excitatory neuron with a self-recurrent connection wired together with an inhibitory neuron through excitatory and inhibitory synapses. The self-recurrent connection of the excitatory neuron mitigates the information loss caused by the firing-and-resetting mechanism and maintains the long-term neuronal memory. The lateral inhibition from the inhibitory neuron to the corresponding excitatory neuron, on the one hand, adjusts the firing activity of the latter. On the other hand, it plays as a forget gate to clear the memory of the excitatory neuron. Based on speech and image datasets commonly used in neuromorphic computing, RSNNs based on the proposed LISR improve performance significantly by up to 9.26% over feedforward SNNs trained by a state-of-the-art backpropagation method with similar computational costs.
  3. Due to their non-volatility 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.
  4. Advances in machine intelligence have sparked interest in hardware accelerators to implement these algorithms, yet embedded electronics have stringent power, area budgets, and speed requirements that may limit nonvolatile memory (NVM) integration. In this context, the development of fast nanomagnetic neural networks using minimal training data is attractive. Here, we extend an inference-only proposal using the intrinsic physics of domain-wall MTJ (DW-MTJ) neurons for online learning to implement fully unsupervised pattern recognition operation, using winner-take-all networks that contain either random or plastic synapses (weights). Meanwhile, a read-out layer trains in a supervised fashion. We find our proposed design can approach state-of-the-art success on the task relative to competing memristive neural network proposals, while eliminating much of the area and energy overhead that would typically be required to build the neuronal layers with CMOS devices.
  5. Spintronic devices, especially those based on motion of a domain wall (DW) through a ferromagnetic track, have received a significant amount of interest in the field of neuromorphic computing because of their non-volatility and intrinsic current integration capabilities. Many spintronic neurons using this technology have already been proposed, but they also require external circuitry or additional device layers to implement other important neuronal behaviors. Therefore, they result in an increase in fabrication complexity and/or energy consumption. In this work, we discuss three neurons that implement these functions without the use of additional circuitry or material layers.