This visualises how modern statistical inference actually works. RJMCMC explores spaces where we don't even know how many parameters we need, perfect for art, where we don't know in advance how many strokes capture an image.
I built an MCMC painter!
I'm excited to share this project I've been working on for a long time, which sits at the intersection of computational statistics and generative art; mcmcPainter!
Link here: mcmcpainter.davidhodgson.me
Upload an image, and the algorithms "paints", one probabilistic brushstroke at a time. Each brushstroke represents a "birth" or "death" jump in the model space:
- The algorithm proposes adding new strokes or removing existing ones
It serves as a nice reminder to me that some of the most elegant solutions in machine learning and statistics aren't always the newest deep learning architectures. Sometimes, good old Bayesian inference with smart sampling strategies can create something really cool!
- Proposals are accepted/rejected based on how well they reconstruct your image
- The final painting emerges from thousands of probabilistic decisions
- It's not deterministic, run it twice -> get two different artworks
New pre-print with @dchodge.bsky.social @thushan-desilva.bsky.social and others looks at SARS-CoV-2 antibody kinetics and correlates of protection in The Gambia. What can different biomarkers tell us about protection in population where >80% infections asymptomatic?
www.medrxiv.org/content/10.6...
Getting started on Substack, just some rambling on Yoga Philosophy and a academia. Give me a follow if interested and share yours too! Open to reading anything 😊 open.substack.com/pub/themindf...
Great to see the seroanalytics.org collection expanding with @dchodge.bsky.social 's work on seroCOP (R package for analysing correlates of protection using Bayesian methods)
🌟 Excited to share my first PhD publication! 🌟
Our paper in Epidemics uses a mathematical model + Scottish surveillance data to understand what COVID-19 pandemic disruptions revealed about RSV disease in young children.
We have our first epinowcast seminar of 2026 today at 3 pm UK time/4 pm in Central Europe. Excited to hear from @dchodge.bsky.social who will discuss tools for serological inference! www.epinowcast.org/seminars/202...