Sitemap

Short description of portfolio item number 1

Short description of portfolio item number 2

We establish a formal connection between the two seminal decompositions using ideas from statistical learning theory and information geometry.

We propose a metric learning scheme to enhance Clifford Group Equivariant Neural Networks, motivated using insights from category theory to guarantee its soundness.

We track the Shannon entropy of intermediate predictions in transformers and use them to uncover consistent computational patterns.

We use techniques from representation theory to uncover what structure neural networks tend to learn, finding a strong preference for the regular representation. Building on this insight, we propose a simple method to enforce approximate equivariance with strong experimental results.

Invited speaker to lead the “Introduction to Mechanistic Interpretability” workshop.

‘Sandwich’ seminar series at CLASH (Cambridge Logic And Semantics Hub)

Supervised 3 groups in Michaelmas 2024.

Supervised 5 groups in Lent 2024.

Supervised 3 groups in Easter 2025.