I finally had a chance to do something I’ve been meaning to do for a long time: post some notebooks on machine learning on GitHub. IPython notebooks are a great way to mix text, math, and code. I’ve been writing ipython notebooks for a while to teach myself some machine learning concepts; there’s no better way to learn than to try to explain something to someone else.
I posted two notebooks to start with: one on contextual bandits, and another on fitting maximum entropy models by persistent contrastive divergence. I’ve got a couple more in the bank, and several more in various states of disarray that I hope to clean up and post.
Stay tuned for more!