Pen and Paper Exercises in Machine Learning

TL;DR

This paper compiles a series of pen-and-paper exercises covering fundamental topics in machine learning, aimed at deepening understanding through theoretical practice.

Contribution

It provides a comprehensive set of exercises across key machine learning concepts, serving as a valuable educational resource.

Findings

Enhances understanding of graphical models and inference methods

Clarifies the theoretical foundations of sampling and variational inference

Supports learning through practical exercises in core ML topics

Abstract

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.