Skip to main content

Benchmarks for Bayesian Deep Learning: Astrophysics


Suitable for

MSc in Computer Science
Mathematics and Computer Science, Part C
Computer Science and Philosophy, Part C
Computer Science, Part C


Bayesian deep learning (BDL) is a field of Machine Learning where we develop tools that can reason about their confidence in their predictions. A main challenge in BDL is comparing different tools to each other, with common benchmarks being much needed in the field. In this project we will develop a set of tools to evaluate Bayesian deep learning techniques, reproduce common techniques in BDL, and evaluate them with the developed tools. The tools we will develop will rely on downstream tasks that have made use of BDL in real-world applications such as parameter estimation in Strong Gravitational Lensing with neural networks. Prerequisites: only suitable for someone who has done Probability Theory, has worked in Machine Learning in the past, and has strong programming skills (Python).