Hi! I’m a PhD student at the BakerLab, University of Washington. I develop protein design methodologies to solve disease and climate change. I obtained my Master’s in 2024 from Oxford in chemistry, specialising in generative models for amorphous materials for my thesis. TTC is a small collection of essays of mine within ML; it’s very much a work in progress, but I’ve found it a nice outlet for some unshared thoughts and getting some writing practise in. Do send me a message if you want to continue the conversation! Also, do check out my links, CV and whatnot here. -Jasper
Introduction
Introduction Machine learning is inherently simple. Take a random matrix, apply it to your input and calculate a number that is proportional to how close you are to your target for said input. Now use an automatic differentiation package to take care of the calculus for you to figure out how much you need to change the parameters to get a better matrix. Repeat this enough times and you’re on your way to the vast majority of deep learning algorithms....
On building diffusion models
BioRXiv DOI https://doi.org/10.1101/2025.08.14.670328 | Summary on X Introduction As of the time of writing, we’ve just released RFdiffusion3’s preprint. A component I often feel is missing from papers is the journey that went on behind the scenes. I went into the field of building models 3 years ago completely blind, and would’ve loved to know what it looks like on the inside. With this article, I wanted to share to share some of the experiences we had, and how this project changed the way I thought about building generative models to solve real world problems....