In Raw Numpy: t-SNE

This is the first post in the In Raw Numpy series. This series is an attempt to provide readers (and myself) with an understanding of some of the most frequently-used machine learning methods by going through the math and intuition, and implementing it using just python and numpy. You can find the full code accompanying this post here. This means we can take some data that lives in a high-dimensional space (such as images, which usually consist of thousands of pixels), and visualise it in a lower-dimensional space. This is desirable, as humans are much better at understanding data when it is presented in a two- or three-dimensional space.