This project is about the training and evaluation of different classifiers and explainable AI approaches on a medical data set. Specifically, the data consists of medical life data (EKG, ...) and class labels in the form of (partial) diagnoses or interventions. The aim is to identify the best classifiers that, on the one hand, make the fewest mistakes in the classification of test data and, on the other hand, provide explanations that are easy to understand and provide plausible justifications for the classification. Expert advice from a medical doctor for the evaluation can be made possible.
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-GP Grundlagenprojekt Intelligente Systeme | Gruppenprojekt | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.