Multilayer spintronic neural networks with radiofrequency connections - CNRS - Centre national de la recherche scientifique
Article Dans Une Revue Nature Nanotechnology Année : 2023

Multilayer spintronic neural networks with radiofrequency connections

Andrew Ross
  • Fonction : Auteur
Nathan Leroux
Arnaud de Riz
  • Fonction : Auteur
Dédalo Sanz-Hernández
Juan Trastoy
  • Fonction : Auteur
Paolo Bortolotti
  • Fonction : Auteur
Damien Querlioz
Leandro Martins
  • Fonction : Auteur
Luana Benetti
Marcel Claro
  • Fonction : Auteur
Pedro Anacleto
Alejandro Schulman
Thierry Taris
  • Fonction : Auteur
Jean-Baptiste Begueret
  • Fonction : Auteur
Sylvain Saïghi
  • Fonction : Auteur
Alex Jenkins
Ricardo Ferreira

Résumé

Spintronic nano-synapses and nano-neurons perform neural network operations with high accuracy thanks to their rich, reproducible and controllable magnetization dynamics. These dynamical nanodevices could transform artificial intelligence hardware, provided they implement state-of-the-art deep neural networks. However, there is today no scalable way to connect them in multilayers. Here we show that the flagship nano-components of spintronics, magnetic tunnel junctions, can be connected into multilayer neural networks where they implement both synapses and neurons thanks to their magnetization dynamics, and communicate by processing, transmitting and receiving radiofrequency signals. We build a hardware spintronic neural network composed of nine magnetic tunnel junctions connected in two layers, and show that it natively classifies nonlinearly separable radiofrequency inputs with an accuracy of 97.7%. Using physical simulations, we demonstrate that a large network of nanoscale junctions can achieve state-of-the-art identification of drones from their radiofrequency transmissions, without digitization and consuming only a few milliwatts, which constitutes a gain of several orders of magnitude in power consumption compared to currently used techniques. This study lays the foundation for deep, dynamical, spintronic neural networks.

Dates et versions

hal-04270425 , version 1 (04-11-2023)

Identifiants

Citer

Andrew Ross, Nathan Leroux, Arnaud de Riz, Danijela Marković, Dédalo Sanz-Hernández, et al.. Multilayer spintronic neural networks with radiofrequency connections. Nature Nanotechnology, 2023, 18, pp.1273-1280. ⟨10.1038/s41565-023-01452-w⟩. ⟨hal-04270425⟩
40 Consultations
0 Téléchargements

Altmetric

Partager

More