A six-part lecture series delivered to the Mayo Clinic Department of Radiation Oncology, designed to introduce clinicians to the foundations of AI, from linear regression and neural networks to medical imaging AI and ChatGPT. No prior AI background is assumed. Watch the full series here.

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Along with Leon Klein, I presented our NeurIPS 2023 spotlight paper on using deep learning to accelerate molecular dynamics simulation.

Learning on Graphs and Geometry (LoGG) reading group:

Molecular Modeling and Drug Discovery (M2D2) reading group:

An Introduction to PAC-Bayes (Cambridge Machine Learning Reading Group)

Along with David Burt and Javier Antoran, I gave an introductory talk on the statistical learning framework and PAC-Bayes. Link to slides.

Understanding Approximate Inference in Bayesian Neural Networks: A Joint Talk

Together with Sebastian Farquhar, I gave a talk on my NeurIPS 2020 paper on approximate inference in BNNs. Our talks present different perspectives on the effectiveness of the mean-field approximation in these models. Link to slides.

On the Expressiveness of Approximate Inference in Bayesian Neural Networks (NeurIPS 2020)

A short video explaining my NeurIPS 2020 paper on BNN inference. SlidesLive link.

Meta-learning Stationary Stochastic Process Prediction with Convolutional Neural Processes (NeurIPS 2020)

A short video explaining my NeurIPS 2020 paper on neural processes. SlidesLive link.

Neural Processes (Cambridge Machine Learning Reading Group)

A reading group talk given with Sebastian Ober and Stratis Markou, introducing various neural processes and covering much of the material in this blog post. Slides.

Recent Advances in Bayesian Deep Learning (Cambridge Machine Learning Reading Group)

A reading group talk given with Siddharth Swaroop, covering modern stochastic gradient Markov chain Monte Carlo (SGMCMC) and natural gradient variational inference methods for Bayesian deep learning. Slides.

‘In-between’ Uncertainty in Bayesian Neural Networks (Contributed talk at ICML 2019 Workshop on Uncertainty in Deep Learning)

This is a short talk explaining my workshop paper on the lack of ‘in-between’ uncertainty when using the mean-field approximation in BNNs. Video (begins at 28:30), slides.

Implicit Variational Inference (Cambridge Machine Learning Reading Group)

With David Burt, I gave a reading group presentation introducing implicit variational inference, a way to obtain very flexible approximate posterior distributions. Slides.