I'm building neural networks that generate provably correct code, and the software infrastructure for training them.

My work is driven by a long-term research programme on Categorical Deep Learning. I pursue this work through Coend, a company I founded dedicated to it. I am also affiliated with Glasgow Lab for AI Verification, where I work on structured tactics for theorem proving.

I hold a PhD in computer science, with a specialisation in category theory. My thesis "Fundamental Components of Deep Learning: A category-theoretic approach" is work I am extremely proud of, go check it out!

I like to build things from ground up, check out my Github. I am also active on Mathstodon and BlueSky.

Posts

• My PhD Thesis is out! - March 13, 2024
• Two kinds of Prisms - February 12, 2023
• Graph Convolutional Neural Networks as Parametric CoKleisli morphisms - December 5, 2022
• Optics vs Lenses, Operationally - February 10, 2022
• Lenses to the left of me, Prisms to the right - January 5, 2022
• Meta-learning and Monads - October 13, 2021
• Riding upon the fields on the horse of mathematics - August 15, 2021
• Towards Categorical Foundations of Learning - March 3, 2021
• Dinatural transformations - September 12, 2019

…or you can find more in the archives.