Priors in bayesian deep learning: A review

V Fortuin - International Statistical Review, 2022 - Wiley Online Library
While the choice of prior is one of the most critical parts of the Bayesian inference workflow,
recent Bayesian deep learning models have often fallen back on vague priors, such as …

Stochastic character mapping, Bayesian model selection, and biosynthetic pathways shed new light on the evolution of habitat preference in cyanobacteria

G Bianchini, M Hagemann… - Systematic …, 2024 - academic.oup.com
Cyanobacteria are the only prokaryotes to have evolved oxygenic photosynthesis paving the
way for complex life. Studying the evolution and ecological niche of cyanobacteria and their …

Single station seismic event location with a neural‐guided mixture model: Model‐based weighting for improved accuracy

JD Castro, C Meneses‐Ponce, R Ortega… - Journal of …, 2024 - Wiley Online Library
In many regions of the world with complex seismic activity, the availability of seismic stations
is limited. This motivated us to develop a probabilistic method for single‐station earthquake …

[PDF][PDF] On the Choice of Priors in Bayesian Deep Learning

V Fortuin - 2021 - research-collection.ethz.ch
Deep learning has positioned itself as one of the most promising directions of machine
learning in recent years. Nonetheless, deep neural networks have many shortcomings, for …