xAI-Proj-B: Bachelorprojekt Erklärbares Maschinelles Lernen

Dozent/in:

Sebastian Dörrich

Angaben:

Projektseminar, 4,00 SWS, ECTS: 6

Termine:

Do, 14:00 - 18:00, WE5/04.003

xAI-Sem-B1: Bachelorseminar Erklärbares Maschinelles Lernen

Dozent/in:

Christian Ledig

Angaben:

Seminar, 2,00 SWS, ECTS: 3

Termine:

Mo, 16:00 - 18:00, WE5/05.005

Voraussetzungen / Organisatorisches:

Interest and registration
Email with name, matriculation number, degree program to christian.ledig@uni-bamberg.de before 29.4.2024.

Eligibility B.Sc. AI, B.Sc. SoSySc, (B.Sc. WI only after prior consultation with the examination office), (potentially also as MSc CitH course)

VC Course https://vc.uni-bamberg.de/course/view.php?id=67941

Inhalt:

Focus Topic in SS 2024: Evaluation of AI models

Motivation
In this seminar, we will focus on approaches for evaluating different kinds of AI models. The careful quantitative assessment of the performance of an AI model is of critical importance to ensure its safe deployment in real-world settings. It is further the foundation of scientific research, enabling researchers to assess the impact of algorithmic changes and compare the performance of an AI system to the state of the art. Most importantly, objective, thorough evaluation allows the identification of biases and weaknesses in the system that would be problematic in practice, potentially putting the user or patient at risk.

Goals and Topics You will learn about established evaluation measures for different types of AI algorithms with a focus on the domain of computer vision and medical image processing. Specifically you will learn how to evaluate algorithms for: image classification, object detection and image segmentation. You will further have the opportunity to learn about common pitfalls, data biases, ground truthing, cross-validation and important considerations when creating datasets for evaluation.

Time and location
Monday (4-6pm) in WE5/05.005;
Initial Meeting (general info): 15.04;
Second Meeting (mandatory for participants): 22.04.