The impressive success of Deep Learning (DL) in predictive performance tasks has fueled the hopes that this can help addressing societal challenges by supporting sound decision making. However, many open questions remain about their suitability to hold up to this promise. In this talk, I will discuss some of the current limitations of DL, which directly affect their wide adoption. I will focus in particular on the poor ability of DL models to quantify uncertainty in predictions, and I will present Bayesian DL as an attractive approach combining the flexibility of DL with probabilistic reasoning. I will then discuss the challenges associated with carrying out inference and specifying sensible priors for DL models. After presenting a few of my contributions to address these problems [1, 2, 3], I will conclude by presenting some interesting emerging research trends and open problems.
Priors for Bayesian deep learning
SIMAI 2023, Italian Society of Applied and Industrial Mathematics, 28 August-1 September 2023, Matera, Italy
© EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in SIMAI 2023, Italian Society of Applied and Industrial Mathematics, 28 August-1 September 2023, Matera, Italy and is available at :
PERMALINK : https://www.eurecom.fr/publication/7387