Publications

Filter by type:
. Towards Automatic Circuit Discovery for mechanistic interpretability. Automatic Circuit DisCovery, 2023.

Preprint Code

. Causal Scrubbing: a method for rigorously testing interpretability hypotheses. Causal Scrubbing, 2022.

Preprint

. Thesis: Priors in finite and infinite Bayesian convolutional neural networks. PhD Thesis, 2022.

PDF

. Understanding Variational Inference in Function-Space. Submitted to AABI, 2020.

Preprint

. Deep Convolutional Networks as shallow Gaussian Processes. Poster in ICLR, 2019.

Preprint Code Poster Slides

. Probability density imputation of missing data with Gaussian Mixture Models. MSc Thesis, 2017.

PDF

. Solving Montezuma's Revenge with Planning and Reinforcement Learning. BSc Thesis, 2016.

PDF Code Slides Video