Rapid learning with phase-change memory-based in-memory computing through learning-to-learn

Thomas Ortner, Horst Petschenig, Athanasios Vasilopoulos, Roland Renner, Špela Brglez, Thomas Limbacher, Enrique Piñero, Alejandro Linares-Barranco, Angeliki Pantazi and Robert Legenstein ()
Additional contact information
Thomas Ortner: IBM Research Europe - Zurich
Horst Petschenig: Graz University of Technology
Athanasios Vasilopoulos: IBM Research Europe - Zurich
Roland Renner: Graz University of Technology
Špela Brglez: Graz University of Technology
Thomas Limbacher: Graz University of Technology
Enrique Piñero: Universidad de Sevilla
Alejandro Linares-Barranco: Universidad de Sevilla
Angeliki Pantazi: IBM Research Europe - Zurich
Robert Legenstein: Graz University of Technology

Nature Communications, 2025, vol. 16, issue 1, 1-16

Abstract: Abstract There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at deployment site. However, current AI models struggle in such scenarios, often requiring extensive fine-tuning, computational resources, and data. In contrast, humans can effortlessly adjust to new tasks by transferring knowledge from related ones. The concept of learning-to-learn (L2L) mimics this process and enables AI models to rapidly adapt with only little computational effort and data. In-memory computing neuromorphic hardware (NMHW) is inspired by the brain’s operating principles and mimics its physical co-location of memory and compute. In this work, we pair L2L with in-memory computing NMHW based on phase-change memory devices to build efficient AI models that can rapidly adapt to new tasks. We demonstrate the versatility of our approach in two scenarios: a convolutional neural network performing image classification and a biologically-inspired spiking neural network generating motor commands for a real robotic arm. Both models rapidly learn with few parameter updates. Deployed on the NMHW, they perform on-par with their software equivalents. Moreover, meta-training of these models can be performed in software with high-precision, alleviating the need for accurate hardware models.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-56345-4 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-56345-4

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-56345-4

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().