## Posts

### Approximate inference via variational autoencoders

A modern classic connecting probabilistic inference and deep learning.### Dimensionality reduction via principal component analysis

We cover another 'classical' technique, this time for unsupervised learning.### Bias-variance trade-off and the interpolating regime

Reproducing a nice result from a recent paper.### Sampling b*sics

We on a roll cos ya basic.### Revisiting the bias-variance decomposition

Another machine-learning classic before we move onto more advanced topics.### Back to basics with Pandas

A simple end-to-end example using the scientific python stack.### Mastering the basics is very underrated

Rebooting the blog with some spicy opinions.### Bay Area II: CFAR Workshop

Apparently the most memorable things I learnt at CFAR were the games.### Simplicity is complicated; contraints bring freedom

Ruminations on Pike, Strunk, and White.### A response to 'The AI Cargo Cult'

A short rebuttal to a recent essay.### AIXIjs

A web demo for general reinforcement learning.### Bay Area I: San Francisco, Berkeley, & Silicon Valley

A short travel post documenting the first half of my Bay area trip.### Marginalization with Einstein

In this post we explore a convenient trick for marginalizing discrete distributions in directed acyclic graphs using NumPy's Einstein summation API.### Linear regression & Hello World!

A brief look at some cool results that are often overlooked in short treatments of linear regression. Also, my first blog post! Yay :)

subscribe via RSS