<p>The nearest neighbor problem is very common in data science. It's useful in recommender situations but also with neural embeddings in general. It's an expensive thing to calculate so it is common to calculate approximate distances as a proxy. In python a very likeable tool for this is <a href="https://github.com/spotify/annoy">annoy</a>.</p>

1 - Intro
2 - Code
3 - Plotting
4 - How it Works 1
5 - How it Works 2
6 - Accuracy
7 - Benchmark
8 - Final Features

The repository (and readme) for annoy can be found here.