Oscillatory neural network learning for pattern recognition: an on-chip learning perspective and implementation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Frontiers in Neuroscience Année : 2023

Oscillatory neural network learning for pattern recognition: an on-chip learning perspective and implementation

Résumé

In the human brain, learning is continuous, while currently in AI, learning algorithms are pre-trained, making the model non-evolutive and predetermined. However, even in AI models, environment and input data change over time. Thus, there is a need to study continual learning algorithms. In particular, there is a need to investigate how to implement such continual learning algorithms on-chip. In this work, we focus on Oscillatory Neural Networks (ONNs), a neuromorphic computing paradigm performing auto-associative memory tasks, like Hopfield Neural Networks (HNNs). We study the adaptability of the HNN unsupervised learning rules to on-chip learning with ONN. In addition, we propose a first solution to implement unsupervised on-chip learning using a digital ONN design. We show that the architecture enables efficient ONN on-chip learning with Hebbian and Storkey learning rules in hundreds of microseconds for networks with up to 35 fully-connected digital oscillators.
Fichier principal
Vignette du fichier
fnins-17-1196796.pdf (1.96 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04129945 , version 1 (16-11-2023)

Licence

Paternité

Identifiants

Citer

Madeleine Abernot, Nadine Azemard, Aida Todri-Sanial. Oscillatory neural network learning for pattern recognition: an on-chip learning perspective and implementation. Frontiers in Neuroscience, 2023, 17, pp.119679. ⟨10.3389/fnins.2023.1196796⟩. ⟨hal-04129945⟩
56 Consultations
10 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More