Explainable Artificial Intelligence (xAI) and model interpretability

Outline

Understanding why a certain model makes certain decisions is key for certain industries such as medicine, law, or finance. This seminar serves as an introduction to these topics and the most commonly used techniques.

Syllabus

  • Introduction and context
  • What is interpretability in ML models?
  • Interopretability techniques
  • Case study

Assessment Method

Attendance, participation and assignment.

Prerequisites

During the course Moodle will be used, so prior to the start of the course it will be necessary for the students to be logged into Moodle with their University credentials.

Credits

0.5 ECTS

Timetable

  • 22 April, 15:00-18:00

Lecture Theatre

  • A-6205

Tuition Language

English.


Subscription to this seminar:

To subscribe to this seminar, please, fill in this fields (use only your UPM email):