A Bayesian neural network approach to Multi-fidelity surrogate modelling - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

A Bayesian neural network approach to Multi-fidelity surrogate modelling

Résumé

This paper deals with surrogate modelling of a computer code output in a multi-fidelity context, i.e., when the output can be evaluated at different levels of accuracy and computational cost. Using observations of the output at low-and high-fidelity levels, we propose a method that combines Gaussian process (GP) regression and Bayesian neural network (BNN), in a method called GPBNN. The low-fidelity output is treated as a single-fidelity code using classical GP regression. The high-fidelity output is approximated by a BNN that incorporates, in addition to the high-fidelity observations, well-chosen realisations of the low-fidelity output emulator. The predictive uncertainty of the final surrogate model is then quantified by a complete characterisation of the uncertainties of the different models and their interaction. GPBNN is compared with most of the multi-fidelity regression methods allowing to quantify the prediction uncertainty.
Fichier principal
Vignette du fichier
GPBNN.pdf (670.35 Ko) Télécharger le fichier
pendulum.png (54.79 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03608580 , version 1 (14-03-2022)
hal-03608580 , version 2 (04-12-2023)

Identifiants

  • HAL Id : hal-03608580 , version 1

Citer

Baptiste Kerleguer, Claire Cannamela, Josselin Garnier. A Bayesian neural network approach to Multi-fidelity surrogate modelling. 2022. ⟨hal-03608580v1⟩
321 Consultations
495 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More