Bayesian Optimization Using Hamiltonian Dynamics for Sparse Artificial Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Bayesian Optimization Using Hamiltonian Dynamics for Sparse Artificial Neural Networks

Résumé

Artificial Neural Networks (ANN) are being widely used in supervised Machine Learning (ML) to analyse signals or images for many applications. Using a learning database, one of the main challenges is to optimize the network weights. This optimization step is generally performed using a gradient-based approach with a back-propagation strategy. For the sake of efficiency, regularization is generally used. When non-smooth regularizers are used especially to promote sparse networks, this optimization becomes challenging. Classical gradient-based optimizers cannot be used due to differentiability issues. In this paper, we propose an MCMC-based optimization scheme formulated in a Bayesian frame-work. Hamiltonian dynamics are used to design an efficient sampling scheme. Promising results show the usefulness of the proposed method to allow ANNs with low complexity levels reaching high accuracy rates.
Fichier principal
Vignette du fichier
Bayesian_Optimization_Using_Hamiltonian_Dynamics_for_Sparse_Artificial_Neural_Networks.pdf (707.41 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03858776 , version 1 (21-11-2022)

Identifiants

Citer

Mohamed Fakhfakh, Bassem Bouaziz, Faïez Gargouri, Lotfi Chaâri. Bayesian Optimization Using Hamiltonian Dynamics for Sparse Artificial Neural Networks. 19th International Symposium on Biomedical Imaging (ISBI 2022), IEEE Signal Processing Society (SPS); IEEE Engineering in Medicine and Biology Society (EMBS), Mar 2022, Kolkata, India. pp.1-4, ⟨10.1109/ISBI52829.2022.9761469⟩. ⟨hal-03858776⟩
31 Consultations
95 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More