EUVIMEDEUVIMED entdecken
Crossref

A design of magnetic tunnel junctions for the deployment of neuromorphic hardware for edge computing

Davi Rodrigues, Eleonora Raimondo, Riccardo Tomasello, Mario Carpentieri, Giovanni Finocchio

Applied Physics Letters · 01.03.2025 · 126 (9)

DOI: 10.1063/5.0237090 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Physics Letters, online erschienen am 03.03.2025. Verfasst von Davi Rodrigues und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Horizon 2020 Framework Programme, Ministero dell'Università e della Ricerca.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The electrically readable complex dynamics of robust and scalable magnetic tunnel junctions (MTJs) offer promising opportunities for advancing neuromorphic computing. In this work, we present an MTJ design with a free layer and two polarizers capable of computing the sigmoidal activation function and its gradient at the device level. This design enables both feedforward and backpropagation computations within a single device, extending neuromorphic computing frameworks previously explored in the literature by introducing the ability to perform backpropagation directly in hardware. Our algorithm implementation reveals two key findings: (i) the small discrepancies between the MTJ-generated curves and the exact software-generated curves have a negligible impact on the performance of the backpropagation algorithm, (ii) the device implementation is highly robust to inter-device variation and noise, and (iii) the proposed method effectively supports transfer learning and knowledge distillation. To demonstrate this, we evaluated the performance of an edge computing network using weights from a software-trained model implemented with our MTJ design. The results show a minimal loss of accuracy of only 0.4% for the Fashion MNIST dataset and 1.7% for the CIFAR-100 dataset compared to the original software implementation. These results highlight the potential of our MTJ design for compact, hardware-based neural networks in edge computing applications, particularly for transfer learning.

Förderung

  • Horizon 2020 Framework Programme
  • Ministero dell'Università e della Ricerca

Zitieren

APA

Rodrigues, D., Raimondo, E., Tomasello, R., Carpentieri, M., & Finocchio, G. (2025). A design of magnetic tunnel junctions for the deployment of neuromorphic hardware for edge computing. Applied Physics Letters, 126(9). https://doi.org/10.1063/5.0237090

Vancouver

Rodrigues D, Raimondo E, Tomasello R, Carpentieri M, Finocchio G. A design of magnetic tunnel junctions for the deployment of neuromorphic hardware for edge computing. Applied Physics Letters. 2025;126(9). doi:10.1063/5.0237090

BibTeX
@article{Rodrigues2025,
  author = {Rodrigues, Davi and Raimondo, Eleonora and Tomasello, Riccardo and Carpentieri, Mario and Finocchio, Giovanni},
  title = {A design of magnetic tunnel junctions for the deployment of neuromorphic hardware for edge computing},
  journal = {Applied Physics Letters},
  year = {2025},
  volume = {126},
  number = {9},
  doi = {10.1063/5.0237090}
}
Kostenlos starten →