|
Instructors: Prof. Dr.-Ing. Joachim Metternich
Event type:
Tutorial
Org-unit: Dept. 16 - Mechanical Engineering
Displayed in timetable as:
Tut Software Eng
Subject:
Crediting for:
Hours per week:
4
Language of instruction:
Englisch
Min. | Max. participants:
- | -
Digital Teaching:
Subject to the dynamic Corona situation, the tutorial will be conducted in presence.
For the execution of the exercises in the theory part as well as the processing of the practical part, an own mobile PC/laptop is required.
Course Contents:
The aim of the tutorial is to teach students how to use the methods of machine learning and professional software development in the context of production, both theoretically and practically, using the example of the process learning factory CiP.
Preconditions:
Prior knowledge of programming with Python is required. Unfortunately, no basic course in programming with Python can be given during the tutorial. Lack of previous knowledge will lead to a higher familiarization effort for the programming tasks during the tutorial. References for familiarization with Python will be sent to the participants before the tutorial starts.
Expected Number of Participants:
The number of participants is limited to 15 students. If you are interested, please send an email to tutorium-seml@ptw.tu-darmstadt.de first. As soon as you receive a positive response from the organizers by e-mail, you can register in TuCan.
Official Course Description:
After the students have successfully completed the course unit, they should be able to develop software for solving manufacturing-related problems using machine learning, while complying with the specifications of time, quality and cost.
The students are enabled to:
- Explain and independently apply methods and tools of professional software development.
- Use of the Python programming language
- Basics of object-oriented programming
- Use of software testing for quality assurance
- Use of the Git version control software
- Use of the Linux OS for development
- Explain and independently apply machine learning methods and tools in the context of production.
- Apply established process models (CRISP-DM, etc.)
- Explain and select appropriate machine learning approaches (regression, classification, etc.) for given use cases
- Explain and select appropriate Deep Learning approaches for given use cases
- Use of relevant Python libraries in the context of machine learning (NumPy, Pandas, scikit-learn, Keras)
- Develop and implement selected solutions to problems in the context of manufacturing together as a team.
- Compile, present and critically evaluate the results.
|
