|
|
Einrichtungen >> Fakultät Wirtschaftsinformatik / Angewandte Informatik >> Bereich Angewandte Informatik >>
|
Lehrstuhl für Erklärbares Maschinelles Lernen
| |
xAI-MML-M Mathematics for Machine Learning -
- Dozent/in:
- Christian Ledig
- Angaben:
- Vorlesung, 2,00 SWS, ECTS: 6
- Termine:
- Di, 12:00 - 14:00, WE5/00.019
- Voraussetzungen / Organisatorisches:
- Degree Programs: MSc AI/CitH/WI/ISSS
No specific prior knowledge is required, but the following will be helpful.
- Working knowledge of programming (e.g., in Python).
- Completion of mathematical courses addressing concepts of linear algebra (e.g., KTR-MfI-2), calculus (e.g., WiMa-B-002), or statistics (e.g., Stat-B).
- Inhalt:
- Content
The course aims to establish a common mathematical foundation for the further study of advanced machine learning techniques. The content is selected specifically to be most relevant for students interested in machine learning problems and covers a broad range of concepts from, e.g., linear algebra, vector calculus, probability theory, statistics, and optimization.
Goals
In this course students will learn fundamental mathematical concepts that are important prerequisites for the deeper understanding of the field of machine learning. The overarching goal of this course is to build a mathematical foundation by selectively covering the most essential mathematical concepts form a broad range of mathematical disciplines. Dependent on previous background, students will get the chance to learn critical ML-relevant mathematics for the first time or consolidate concepts that have been partially covered in their previous curriculum.
The lecture is accompanied by exercises and assignments that will help participants develop both theoretical and practical experience. In those exercises students will get the opportunity to learn how to apply and prove theoretical concepts as well as implement some concrete algorithms in Python and its respective commonly used libraries.
- Empfohlene Literatur:
- Marc. Peter Deisenroth, A. Aldo Faisal, Cheng Soon Ong: Mathematics for Machine Learning, Cambridge University Press, 2020
Further literature will be announced at the beginning of the course.
|
| |
xAI-Sem-B1: Bachelorseminar Erklärbares Maschinelles Lernen -
- Dozent/in:
- Christian Ledig
- Angaben:
- Seminar, 2,00 SWS, ECTS: 3
- Termine:
- Mi, 14:00 - 16:00, WE5/03.004
- Inhalt:
- Focus Topic in SS 2023: 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
Wednesdays (2-4pm) in WE5/03.004;
Initial Meeting (general info): 19.04;
Second Meeting (mandatory for participants): 26.04.
|
|
 |
|
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|