Statistical Machine Learning 1RT700 61808 VT2024

Course content

This is an introductory course to statistical machine learning for students with some background in elementary calculus, linear algebra, and probability theory.

The course is focusing on supervised learning, i.e., classification and regression with real data, and its computational and statistical foundations. In addition to the necessary theory (e.g., derivations and proofs), this course also includes practical sessions (notably the lab and the project). The practical part will be implemented using Python.

The recommended course book is Machine Learning - A First Course for Engineers and Scientists, which is available online free of charge. Certain chapters will be recommended for reading each week. Link to videos and other material are also provided below.

Prerequisite knowledge

Basic probability theory:

The course assumes the students have background in elementary calculus, linear algebra, and probability theory.

The following examples are concepts used in the course and it is expected that the students have some familiarity with them:

• Gradient of a function
• Matrix multiplication
• (Joint) probability distributions of random variables
• Expected value of a random variable
• Conditional probability distribution and conditional expected value
• See the video "Introduction to statistical thinking" on the lecture page

Python introduction:

The course assumes some programming knowledge, and we will use Python throughout the course. Have a look at the following notebook if you need a Python refresher. The notebook provides an introduction to NumPy, Pandas and Matplotlib, and the exercises include explainations that may help you in the first computer class. The notebook and suggested solutions are found here: Notebook, Solutions, Open in colab

We also recomment the "Introduction to Python" crash course linked on the lecture page.