Leveraging a Passive MRAM Crossbar for Hardware-in-the-Loop and Continual learning
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits · 2026 · 12 · 129-134
DOI: 10.1109/jxcdc.2026.3702001 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 2026. Verfasst von M. Drouhin und 10 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon European Innovation Council (EIC) Grant Program.
Abstract (Originalsprache)
Artificial neural networks (ANNs) have enabled major advances in artificial intelligence, yet their growing computational and energy demands challenge conventional von Neumann architectures due to the costly separation of memory and processing. In-memory computing has emerged as a promising solution, particularly through memristive crossbar arrays capable of performing multiply-and-accumulate operations directly within memory. Among nonvolatile memory technologies, magnetic tunnel junctions, the core elements of MRAM, offer high endurance, nonvolatility, and CMOS compatibility, making them attractive candidates for neuromorphic systems. In this work, we report inference results on a $15 \times 15$ MRAM crossbar, benchmarking experimental measurements against numerical simulations. We further demonstrate hardware-in-the-loop (HIL) training and experimentally validate metaplasticity mechanisms enabling continual learning on simple tasks. These results highlight the potential of MRAM-based in-memory architectures for adaptive, energy-efficient, and scalable artificial intelligence (AI) hardware.
Förderung
- European Union’s Horizon European Innovation Council (EIC) Grant Program
Zitieren
APA
Drouhin, M., Grelier, M., Deroo, M., Sassi, Y., Monteblanco, E., Davila, N., Mihajlović, G., Chopdekar, R. V., Santos, T. S., Katine, J. A., & Ravelosona, D. (2026). Leveraging a Passive MRAM Crossbar for Hardware-in-the-Loop and Continual learning. IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 12, 129-134. https://doi.org/10.1109/jxcdc.2026.3702001
Vancouver
Drouhin M, Grelier M, Deroo M, Sassi Y, Monteblanco E, Davila N, et al. Leveraging a Passive MRAM Crossbar for Hardware-in-the-Loop and Continual learning. IEEE Journal on Exploratory Solid-State Computational Devices and Circuits. 2026;12:129-134. doi:10.1109/jxcdc.2026.3702001
BibTeX
@article{Drouhin2026,
author = {Drouhin, M. and Grelier, M. and Deroo, M. and Sassi, Y. and Monteblanco, E. and Davila, N. and Mihajlović, G. and Chopdekar, R. V. and Santos, T. S. and Katine, J. A. and Ravelosona, D.},
title = {Leveraging a Passive MRAM Crossbar for Hardware-in-the-Loop and Continual learning},
journal = {IEEE Journal on Exploratory Solid-State Computational Devices and Circuits},
year = {2026},
volume = {12},
pages = {129--134},
doi = {10.1109/jxcdc.2026.3702001}
}
EUVIMED