Imposing Functional Priors on Bayesian Neural Networks

Bogdan Kozyrskiy, Dimitrios Milios, Maurizio Filippone

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Specifying sensible priors for Bayesian neural networks (BNNs) is key to obtain state-of-the-art predictive performance while obtaining sound predictive uncertainties. However, this is generally difficult because of the complex way prior distributions induce distributions over the functions that BNNs can represent. Switching the focus from the prior over the weights to such functional priors allows for the reasoning on what meaningful prior information should be incorporated. We propose to enforce such meaningful functional priors through Gaussian processes (GPs), which we view as a form of implicit prior over the weights, and we employ scalable Markov chain Monte Carlo (MCMC) to obtain samples from an approximation to the posterior distribution over BNN weights. Unlike previous approaches, our proposal does not require the modification of the original BNN model, it does not require any expensive preliminary optimization, and it can use any inference techniques and any functional prior that can be expressed in closed form. We illustrate the effectiveness of our approach with an extensive experimental campaign.

Original languageEnglish (US)
Title of host publicationICPRAM 2023 - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods, Volume 1
EditorsMaria De Marsico, Gabriella Sanniti di Baja, Ana L.N. Fred
PublisherScience and Technology Publications, Lda
Number of pages8
ISBN (Print)9789897586262
StatePublished - 2023
Event12th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2023 - Lisbon, Portugal
Duration: Feb 22 2023Feb 24 2023

Publication series

NameInternational Conference on Pattern Recognition Applications and Methods
ISSN (Electronic)2184-4313


Conference12th International Conference on Pattern Recognition Applications and Methods, ICPRAM 2023

Bibliographical note

Publisher Copyright:
© 2023 by SCITEPRESS-Science and Technology Publications, Lda.


  • Bayesian Inference
  • Deep Neural Networks
  • Markov Chain Monte-Carlo

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Imposing Functional Priors on Bayesian Neural Networks'. Together they form a unique fingerprint.

Cite this