Automated Machine Learning

Course type:Flipped-classroom Lecture + Exercise
Time:Mondays, 14:00 - 16:00
Location:HS 00 036 SCHICK - SAAL (G.-Köhler-Allee 101)
Organizers:Frank Hutter, Heri Rakotoarison, Neeratyoy Mallik, Eddie Bergman, Johannes Hog, Martin Mráz, Steven Adriaensen, Noor Awad, André Biedenkapp
Web page:HISinOne

First Lecture

Date: Monday, April 15, 2024, 14:15.
Requirement for attending: The Overview lecture from the course website (password to be sent via HISinOne email and first in-person lecture).


Applying machine learning (ML) and in particular deep learning (DL) in practice is a challenging task and requires a lot of expertise. Among other things, the success of ML/DL applications depends on many design decisions, including an appropriate preprocessing of the data, choosing a well-performing machine learning algorithm, and tuning its hyperparameters, giving rise to a complex pipeline. Unfortunately, even experts need days, weeks, or even months to find well-performing pipelines and can still make mistakes when optimizing their pipelines. The course will discuss meta-algorithmic approaches to automatically search for, and obtain well-performing machine learning systems using automated machine learning (AutoML). Such AutoML systems allow for faster development of new ML/DL applications, require far less expert knowledge than doing everything from scratch and often even outperform human developers. In this lecture, you will learn how to use such AutoML systems, develop your own systems, and understand ideas behind state-of-the-art AutoML approaches.


We strongly recommend that you know the foundations of

  • machine learning (ML)
  • and deep learning (DL)

We further recommend that you have hands-on experience with:

  • Python (3.8+)
  • machine learning (scikit-learn)
  • deep learning (PyTorch)

The participants should have attended at least one other course for ML and DL in the past.


The lectures are partitioned into several parts, including:

  • Hyperparameter Optimization
  • Bayesian Optimization for Hyperparameter Optimization
  • Neural Architecture Search
  • Dynamic Configuration
  • Analysis and Interpretability of AutoML
  • Algorithm Selection/Meta-Learning


The course will be taught in a flipped-classroom style. We will meet weekly once for a lecture, and once weekly (optionally) for exercise sessions.

Every week, there will be a new exercise sheet. Most exercises will be practical, and involve programming in Python and teamwork (teams of up to 3 students!) so that you learn how to apply AutoML in practice.

Lecture: Mondays, 14 - 16

Exercise sessions [optional] (hybrid format): Thursdays, 14-16

Exercise submission deadline [strict] (via Github): Tuesdays, 23:59

Course material: The links to access the GitHub classroom repositories, videos with subtitles, and extra lecture materials will be made available on this page. (The password to that page will be announced in the first session and via HISinOne email).

The course will be taught in English.

MOOC content: The material is publicly available via the AI-Campus platform. Please register on AI-Campus to access the materials. Grading of the exercises will be done via GitHub classroom.

The lecture materials are open-sourced via