Event

The dates and events shown here are dynamically displayed from Stud.IP.

Therefore, if you have any questions, please contact the person listed under the item Lehrende/DozentIn (Lecturers) directly.

Event

Semester: Summer term 2024

2.01.5402 Trustworthy Machine Learning -  


Event date(s) | room

  • Donnerstag, 4.4.2024 8:00 - 10:00 | V02 0-002
  • Montag, 8.4.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 11.4.2024 8:00 - 10:00 | V02 0-002
  • Montag, 15.4.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 18.4.2024 8:00 - 10:00 | V02 0-002
  • Montag, 22.4.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 25.4.2024 8:00 - 10:00 | V02 0-002
  • Montag, 29.4.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 2.5.2024 8:00 - 10:00 | V02 0-002
  • Montag, 6.5.2024 12:00 - 14:00 | V02 0-002
  • Montag, 13.5.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 16.5.2024 8:00 - 10:00 | V02 0-002
  • Donnerstag, 23.5.2024 8:00 - 10:00 | V02 0-002
  • Montag, 27.5.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 30.5.2024 8:00 - 10:00 | V02 0-002
  • Montag, 3.6.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 6.6.2024 8:00 - 10:00 | V02 0-002
  • Montag, 10.6.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 13.6.2024 8:00 - 10:00 | V02 0-002
  • Montag, 17.6.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 20.6.2024 8:00 - 10:00 | V02 0-002
  • Montag, 24.6.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 27.6.2024 8:00 - 10:00 | V02 0-002
  • Montag, 1.7.2024 12:00 - 14:00 | V02 0-002
  • Donnerstag, 4.7.2024 8:00 - 10:00 | V02 0-002

Description

Machine learning algorithms find its way into an increasing number of (safety-critical) application domains but their quality is rarely assessed in a systematic way. The focus of this module are quality criteria for machine learning algorithms, in particular of deep neural networks, ranging from performance evaluation over explainability/interpretability (XAI), robustness (adversarial robustness, robustness against input perturbations), uncertainty quantification, distribution shift, domain adaptation, fairness/bias to privacy. The methods are introduced theoretically in the lecture and implemented/applied practically in the exercises. Prerequisites are basic theoretical knowledge in machine learning, programming skills in Python and ideally practical knowledge in training neural networks.

Lecturers

SWS
4

Lehrsprache
deutsch und englisch

(Changed: 19 Jan 2024)  | 
Zum Seitananfang scrollen Scroll to the top of the page