πŸ—“οΈ Week 09 - Anomaly detection

Theme: Unsupervised Learning

Author
Note

This page was updated to fix the link to the lecture notebook.
The lecture notebook was updated to:

  • introduce Isolation Forest before LOF (as we did in the lecture itself)
  • and to clarify the selection of parameters for isolation forest

Welcome to the nineth week of this course!

We finish our exploration of unsupervised learning with yet another family of unsupervised learning: anomaly detection. We will explain in which cases anomaly detection applies before introducing a few techniques of anomaly detection (anomaly detection through clustering, a tree-based anomaly detection technique called isolation forest and a density-based anomaly detection technique called Local Outlier Factor (LOF)).

We’ll be releasing the topic of your last summative (due on W11+1) this week!

πŸ‘©πŸ»β€πŸ« Lecture Material

πŸŽ₯ Looking for lecture recordings? You can only find those on Moodle, typically a day after the lecture. If you can’t find the recordings, please contact πŸ“§ .

Download the Quarto markdown file for this lecture:

Download the dataset for this lecture: