These lecture notes are the core reading material for DD1420 - Foundations of Machine Learning. Each section of these lecture notes covers a different area of machine learning and provides a comprehensive overview of the theory and practice within that area. Topics include optimization, generalization, neural networks, decision making, probability, and much more. The material is designed to be followed sequentially, but it is also possible to skip around as needed.

In addition to the lecture notes, notation, and terminology are also provided to ensure students have a comprehensive understanding of the material.

Notation

Introduction

ML & Optimization

ML & Generalization

ML & Neural Networks

ML & Geometry

ML & Kernel Methods

ML & Probability

ML & Information Theory

ML & Data Generation

A note on how to read the notes. You are free to skip around the lecture notes, as most lessons are self-contained. However, there are cases where knowledge from a previous lesson is assumed. We have also included a system to indicate how important each section is in relation to course assessment:

★★★ Absolutely central to the course ★★☆ Important ★☆☆ Nice to know, might appear in a quiz ☆☆☆ This is for your information but you won’t be examined on it