I’ve worked as project lead, systems designer, maintainer, developer, and researcher, on large and small projects in industry and academia.
I’m big on data engineering, explainable ML/AI, and theoretical and applied stats.
I believe one of the biggest challenges in engineering is to not overcomplicate things - to pick the right problems and strip away complexity, not add more in. It’s iterative, and it’s hard (or impossible?) to get it “right”. The goal posts naturally shift as requirements evolve.
When it comes to stats and machine learning, I tend to focus a lot on uncertainty and decision making. Models help us with experimenting, exploring, explaining, predicting, quantifying uncertainty/volatility, and then ultimately making decisions.
Underneath all that modelling lies all the insane amounts of abstraction we’ve built up to support data flow: creation, collection, storage, structure, automation, interfaces, monitoring, networks, security…
What keeps me engaged is that I always start from the assumption that there are simple elegant solutions to our problems. I think solutions have enough in common, abstractly, that we should invest considerable time in improving how we go about finding and building them.
I love teaching, writing courses and books. my favourite way to teach is in short workshops where I can design the experience and the material. I love getting to the end and knowing I’ve made the experience worthwhile for the people who’ve attended.
In my spare time I enjoy being a dad, surfing, good conversation, and my own coding projects (in Julia, Python, R and SQL, mainly).
“Uncertainty is not an accident of the scientific method, but its substance” — Andrea Saltelli.
“An approximate answer to the right problem is worth a good deal more than an exact answer to an approximate problem” — John Tukey.
“Whenever there is a simple error that most laymen fall for, there is always a slightly more sophisticated version of the same problem that experts fall for.” - Amos Tverski
Fill out the contact form below if you’d like to get in touch.
Download my resumé.
PhD (Statistics/ML/AI), 2024
The University of Queensland
BSc (Honours 1st Class, College Medal in Science), 2018
La Trobe University
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a large extent, to a solid theoretical foundation, including four ``favourable and fair" axioms for attribution in transferable utility games.