Experimentelle Techniken in der Physik gestützt durch Künstliche Intelligenz / Maschinelles Lernen
Titel auf Englisch: Experimental Techniques in Physics Supported with Artificial Intelligence / Machine Learning
Lernergebnisse
After completion of the module, students will have an overview on methods and tools used for experimentation with physical systems. They know the role of artificial intelligence/machine learning (AI/ML) in inference with experimental data processing. They are able to apply the acquired knowledge in computer experiments realized during laboratories.
Inhalte
The subject of the module is the fundamentals of experiment design, including the theoretical and practical aspects of experiment planning and execution. This includes, for example, the role of observation and measurement in cognition process, data collection and processing with the use of statistical and AI/ML methods, data and system modeling, computer simulation, and planning of experiment. The laboratory will use computer simulation to solve selected problems of experimentation, e.g. forward and inverse modeling, signal reconstruction, model identification, experiment planning. Statistical and AI/ML techniques will be used in exemplary tasks. The form of the class includes the realization of tasks under supervision and solving self-defined problems.
Voraussetzungen
Verpflichtende Voraussetzungen
Keine
Empfohlene Voraussetzungen
Knowledge of mathematics, especially statistics
Prüfungsmodalitäten
- Successful completion of the project task, 30 h
- Written examination, 90 min. OR
- Oral examination, 30-45 min. (with small number of participants)
Angeboten in
- Artificial IntelligenceM.Sc.
Wahlpflichtkomplex: Knowledge Acquisition, Representation, and Processing
- PhysicsM.Sc.
Wahlpflichtkomplex: Minor Subject
| Studiengang | Abschluss | Wahlpflichtkomplex |
|---|---|---|
| Artificial Intelligence | M.Sc. | Knowledge Acquisition, Representation, and Processing |
| Physics | M.Sc. | Minor Subject |
Literatur und Materialien
- Brandt S.: Data analysis. Statistical and computational methods for scientists and engineers. 4th Ed., Springer, Heidelberg 2014
- Söderstöm T., Stoica P.: System identification. Prentice Hall, Michigan, USA, 1989
- Lakshmanan V., Robinson S., Munn M.: Machine learning design patterns. Solutions to common challenges in data preparation, model building, and MLOps. O'Reilly, USA 2020
Bewertungen von Studierenden
Was Studierende über dieses Modul sagen. Die BTU hat damit nichts zu tun — hier schreiben nur Studierende, und jede Bewertung ist die Meinung einer einzelnen Person.