|
|
Einrichtungen >> Fakultät Wirtschaftsinformatik / Angewandte Informatik >>
|
Lehrveranstaltungen
| |
xAI-Sem-B1: Bachelorseminar Erklärbares Maschinelles Lernen [xAI-Sem-B1-AIEval] -
- Dozent/in:
- Christian Ledig
- Angaben:
- Seminar, 2 SWS, benoteter Schein, ECTS: 3, for Bachelor and Master
- Termine:
- Mo, 14:00 - 16:00, WE5/04.003
Wir streben an, diese Veranstaltung in Präsenz durchzuführen.
- Voraussetzungen / Organisatorisches:
- Interest and registration
If you have questions or for registration, please send an Email to christian.ledig@uni-bamberg.de
For registration include name and matriculation number.
- Inhalt:
- Focus Topic in SS 2022:
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.
Format
We will meet in the beginning of the semester to discuss possible work areas and assign concrete topics to each participant. You will be provided pointers to literature and then independently familiarize yourself with the assigned topic. Towards the end of the semester you will:
- present your topic as a 30 minute presentation and
- submit a written report of approximately 8 pages.
- The goal is to run the seminar in English including presentations and the written report.
The presentations will be conducted as a block seminar towards the end of the semester.
The weekly hours mentioned in the module description are an optional time slot to get support, guidance and feedback on your topic (as required).
Expected workload & Grading
The time (work load) of this module is expected to be roughly as follows:
- Attendance of seminar / presentation: 20h
- Literature review and familiarization with topic: 25h
- Preparation of presentation: 15h
- Written report: 30h
The grade will be determined in equal parts based on the presentation and report. Attendance of the presentations is mandatory.
|
| |
xAI-Sem-M1: Masterseminar Erklärbares Maschinelles Lernen [xAI-ML4H] -
- Dozent/in:
- Christian Ledig
- Angaben:
- Seminar, 2 SWS, benoteter Schein, ECTS: 3
- Termine:
- Di, 16:00 - 18:00, WE5/05.003
Wir streben an, diese Veranstaltung in Präsenz durchzuführen.
- Voraussetzungen / Organisatorisches:
- Interest and registration
If you have questions or for registration, please send an Email to christian.ledig@uni-bamberg.de
For registration include name and matriculation number.
Requirements:
completed course "Lernende System / Machine Learning" or "Einführung in die KI / Introduction into AI" bestanden
- Inhalt:
- Focus Topic in SS 2022: Machine Learning for Healthcare
Motivation
Machine Learning holds great promise to transform key aspects of healthcare. The motivation is that AI-powered systems have the potential to substantially increase access to affordable healthcare, allow individualized patient-focused treatment plans and support clinical decision makers to reach more accurate and objective decisions faster.
However, there are key challenges when translating AI technology into practice. Those challenges include (among others) technical integration, data privacy, generalization, robustness, transparency, interpretability and patient communication.
Goals and Topics
You will learn about the potential as well as current challenges when translating AI systems into healthcare systems. The focus of the seminar will be biased towards approaches based on computer vision algorithms and medical image processing. Specifically you will learn about the state of the art in specific clinical applications such as pathology, negative examples of AI systems that failed to deliver on promises, regulatory constraints, patient privacy and data management. The seminar will allow you, based on your interest, to focus on a wide spectrum of aspects ranging from recently published technical solutions to the state of affairs on the policy level.
Format
We will meet in the beginning of the semester to discuss possible work areas and assign concrete topics to each participant. You will be provided pointers to literature and then independently familiarize yourself with the assigned topic. Towards the end of the semester you will:
- present your topic as a 30 minute presentation and
- submit a written report of approximately 8 pages.
- The goal is to run the seminar in English including presentations and the written report.
The presentations will be conducted as a block seminar towards the end of the semester.
The weekly hours mentioned in the module description are an optional time slot to get support, guidance and feedback on your topic (as required).
Expected workload & Grading
The time (work load) of this module is expected to be roughly as follows:
- Attendance of seminar / presentation: 20h
- Literature review and familiarization with topic: 25h
- Preparation of presentation: 15h
- Written report: 30h
The grade will be determined in equal parts based on the presentation and report. Attendance of the presentations is mandatory.
|
|
 |
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|