Asynchronous layerwise deep learning with MCMC on low-power devices - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Asynchronous layerwise deep learning with MCMC on low-power devices

Résumé

We present a new architecture to learn a light neural network using an asynchronous layerwise bayesian optimization process deployed on low-power devices. The procedure is based on a sequence of five modules. In each module, an accept-reject algorithm allows to update real-valued-or binary-weights without any back propagation of gradients. The learning process is tested on two different environments and the electricity consumption is evaluated on several epochs, based on a homemade open source library using standard softwares and performance counters, and compared with a physical power meter. It shows that the decentralized version deployed on several low-power devices is more energy-efficient than the standard GP-GPU version on a dedicated server.
Fichier principal
Vignette du fichier
Article (2).pdf (628.21 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04270262 , version 1 (14-11-2023)

Licence

Identifiants

  • HAL Id : hal-04270262 , version 1

Citer

M François, P Gay, S Lebeaud, S Loustau, J Palafox, et al.. Asynchronous layerwise deep learning with MCMC on low-power devices. 2023. ⟨hal-04270262⟩
39 Consultations
55 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More