Exploiting Non-idealities of Resistive Switching Memories for Efficient Machine Learning - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Frontiers in Electronics Année : 2022

Exploiting Non-idealities of Resistive Switching Memories for Efficient Machine Learning

Résumé

Novel computing architectures based on resistive switching memories (also known as memristors or RRAMs) have been shown to be promising approaches for tackling the energy inefficiency of deep learning and spiking neural networks. However, resistive switch technology is immature and suffers from numerous imperfections, which are often considered limitations on implementations of artificial neural networks. Nevertheless, a reasonable amount of variability can be harnessed to implement efficient probabilistic or approximate computing. This approach turns out to improve robustness, decrease overfitting and reduce energy consumption for specific applications, such as Bayesian and spiking neural networks. Thus, certain non-idealities could become opportunities if we adapt machine learning methods to the intrinsic characteristics of resistive switching memories. In this short review, we introduce some key considerations for circuit design and the most common non-idealities. We illustrate the possible benefits of stochasticity and compression with examples of well-established software methods. We then present an overview of recent neural network implementations that exploit the imperfections of resistive switching memory, and discuss the potential and limitations of these approaches.
Fichier principal
Vignette du fichier
Yon_2022_felec-03-825077.pdf (994.82 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03679671 , version 1 (27-05-2022)

Licence

Paternité

Identifiants

Citer

Victor Yon, Amirali Amirsoleimani, Fabien Alibart, Roger Melko, Dominique Drouin, et al.. Exploiting Non-idealities of Resistive Switching Memories for Efficient Machine Learning. Frontiers in Electronics, 2022, 3, pp.825077. ⟨10.3389/felec.2022.825077⟩. ⟨hal-03679671⟩
63 Consultations
68 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More