Shape Anisotropy-Dependent Leaking in Magnetic Neurons for Bio-Mimetic Neuromorphic Computing
ACS Nano · 2025
DOI: 10.1021/acsnano.4c13020 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACS Nano, 2025. Verfasst von Thomas Leonard und 5 weiteren Autor:innen. Beteiligte Einrichtung: Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas 78712, United States. Hauptthemen laut MEDLINE: Neurons, Neural Networks, Computer, Biomimetics. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Science Foundation Graduate Research Fellowship Program, University of Texas at Austin, Sandia National Laboratories.
Abstract (Originalsprache)
Spiking neural networks seek to emulate biological computation through interconnected artificial neuron and synapse devices. Spintronic neurons can leverage magnetization physics to mimic biological neuron functions, such as integration tied to magnetic domain wall (DW) propagation in a patterned nanotrack and firing tied to the resistance change of a magnetic tunnel junction (MTJ), captured in the domain wall-magnetic tunnel junction (DW-MTJ) device. Leaking, relaxation of a neuron when it is not under stimulation, is also predicted to be implemented based on DW drift as a DW relaxes to a low energy position, but it has not been well explored or demonstrated in device prototypes. Here, we study DW-MTJ artificial neurons capable of leaky integrate-and-fire (LIF) behavior and demonstrate geometry-dependent leaking dynamics that results in repeatable, tunable LIF operation. Studying the behavior of five different device designs, we show tuning the geometry, stimulating fields and currents, and location of electrical contacts results in a wide range of neuron behavior. Additionally, implementation of an asymmetric notch allows for nonlinear pinning which increased expressivity without sacrificing leaking. The measured behavior is implemented in a simulated spiking neural network that outperforms a 1D model of continuous DW motion and approaches the performance of an ideal LIF activation function. The results show that the analog LIF capability of DW-MTJ neurons combines many desirable neuron functions into a single device, which can result in varied forms of multifunctional neuromorphic computing.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas 78712, United States.
- Microelectronics Research Center, The University of Texas at Austin, Austin, Texas 78758, United States.
- Sandia National Laboratories, Albuquerque, New Mexico 87123, United States.
ORCID-Profile: Samuel Liu, Jean Anne C Incorvia
Förderung
- National Science Foundation Graduate Research Fellowship Program
- University of Texas at Austin
- Sandia National Laboratories
Zitieren
APA
Leonard, T., Zogbi, N., Liu, S., Rogers, W. S., Bennett, C. H., & Incorvia, J. A. C. (2025). Shape Anisotropy-Dependent Leaking in Magnetic Neurons for Bio-Mimetic Neuromorphic Computing. ACS Nano. https://doi.org/10.1021/acsnano.4c13020
Vancouver
Leonard T, Zogbi N, Liu S, Rogers WS, Bennett CH, Incorvia JAC. Shape Anisotropy-Dependent Leaking in Magnetic Neurons for Bio-Mimetic Neuromorphic Computing. ACS Nano. 2025. doi:10.1021/acsnano.4c13020
BibTeX
@article{Leonard2025,
author = {Leonard, Thomas and Zogbi, Nicholas and Liu, Samuel and Rogers, William S and Bennett, Christopher H and Incorvia, Jean Anne C},
title = {Shape Anisotropy-Dependent Leaking in Magnetic Neurons for Bio-Mimetic Neuromorphic Computing},
journal = {ACS Nano},
year = {2025},
doi = {10.1021/acsnano.4c13020}
}
EUVIMED