This is the story of Fatboy, a neural network that taught itself to play backgammon back in the early 90s. When it connected to the First Internet Backgammon Server (FIBS) 24 hours a day and 7 days a week in the summer of 94, it was probably the first autonomous AI game playing agent on the internet. It wasn’t the strongest backgammon playing network, that title was taken by TD-Gammon and later by JellyFish, but for a while it was the strongest freely available program. It played at a decent level and generated a lot of interest on FIBS when it first appeared.

Estimating expectations with respect to high-dimensional multimodal distributions is difficult. Here we describe an implementation of Hamiltonian annealed importance sampling in TensorFlow and compare it to other annealed importance sampling implementations. This is joint work with Halil Bilgin.

A common problem in computer science is selecting the $k$ largest (or smallest) elements from an unsorted list containing $n$ elements. The most commonly implemented solution is far from optimal. This post describes a better way.