the academic
I decided to write a blog because it's a good way to procrastinate. The academic is about work in progress, small pieces of research that didn't make it into a paper. Feel free to comment, get in touch on Twitter or by email. Thanks for reading!

Gaussian processes like you never saw them

This post was written in a Jupyter notebook, which can be found here The Python code below is heavily inspired by the Javascript implementation here


A big uniform

This post was inspired by something Brendon Brewer said on the ESAC Data Analysis & Statistics Workshop, last week.


Bricks

Chaos in the Brickyard, by Bernard K. Forscher, Mayo Clinic, Rochester, Minnesota • link


Time derivative of the Keplerian function

I started experimenting with the automatic differentiation package autograd and, wow this thing is pretty amazing!


Truncated Distributions

In a Bayesian model, each parameter needs a prior distribution. To set these priors, we sometimes want to use standard probability distributions but constrained to some interval \([a,b]\) inside their support. How to do this?