Pen and Paper Exercises in Machine Learning

This is a collection of (mostly) pen-and-paper exercises in machine learning. The exercises are on the following topics: linear algebra, optimisation, directed graphical models, undirected graphical models, expressive power of graphical models, factor graphs and message passing, inference for hidden Markov models, model-based learning (including ICA and unnormalised models), sampling and Monte-Carlo integration, and variational inference.

The author assumes basic calculus, linear algebra, probability and statistics but no prior exposure to machine learning. The text introduces each method clearly and concisely "from scratch" based on the fundamentals. All methods and algorithms are described by a clean and consistent style, with a minimum of unnecessary detail. Numerous case studies and concrete examples demonstrate how the methods can be applied in a variety of contexts.

"Train a small machine learning model to play chess or a similar game and then actually run that model in real time, pen and paper, entirely by hand, and in so doing, eventually win against an opponent that i couldn’t beat myself."