Machine Learning & Deep Learning
Niveau
Master's degree program
Learning outcomes of the courses/module
The participants:
• can identify tools (e.g., libraries, cloud platforms, or software tools) that can be used to support machine learning
• can compare the tools they have studied with regard to their suitability for specific problems
• can design end-to-end machine learning projects
• can independently carry out end-to-end machine learning projects
• can identify tools (e.g., libraries, cloud platforms, or software tools) that can be used to support machine learning
• can compare the tools they have studied with regard to their suitability for specific problems
• can design end-to-end machine learning projects
• can independently carry out end-to-end machine learning projects
Prerequisites for the course
1st semester: Students have prior knowledge in mathematics/statistics equivalent to 8 ECTS and are therefore familiar with basic statistical measures as well as fundamental statistical test procedures (e.g., t-test). / 2nd semester: No prerequisites / 2nd semester: Module examination MLAL.A1 (Algorithmics 1)
Course content
The following topics are covered in the course:
- Classical neural networks as a complement to classical data science algorithms (e.g., random forests, SCM, etc.)
- Convolutional artificial neural networks (CNN)
- Recurrent artificial neural networks (RNN, LSTM)
- Advanced artificial neural networks (GAN, FARM, BERT, CGAN, etc.)
The network types discussed are subject to constant change. For this reason, only a few network types are mentioned here as examples. In particular, the course also covers and applies current network types.
- Classical neural networks as a complement to classical data science algorithms (e.g., random forests, SCM, etc.)
- Convolutional artificial neural networks (CNN)
- Recurrent artificial neural networks (RNN, LSTM)
- Advanced artificial neural networks (GAN, FARM, BERT, CGAN, etc.)
The network types discussed are subject to constant change. For this reason, only a few network types are mentioned here as examples. In particular, the course also covers and applies current network types.
Recommended specialist literature
- James, G.; Witten, D; Hastie, T.; Tibshirani, R. (2023). An Introduction to Statistical Learning: with Applications with Python (ISBN: 978-3031387463)
- Bruce. P.; Bruce, A.; Gedeck, P. (2020): Practical Statistics for Data Scientists: 50+ Essential Concepts Using R and Python (ISBN: 978-1492072942)
- Geron, A. (2022): Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, (ISBN: 978-1098125974)
- Bruce. P.; Bruce, A.; Gedeck, P. (2020): Practical Statistics for Data Scientists: 50+ Essential Concepts Using R and Python (ISBN: 978-1492072942)
- Geron, A. (2022): Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, (ISBN: 978-1098125974)
Assessment methods and criteria
Portfolio
Language
English
Number of ECTS credits awarded
10
Semester hours per week
Planned teaching and learning method
The following methods are used:
- Working on practice exercises
- Interactive workshop
- Working on practice exercises
- Interactive workshop
Semester/trimester in which the course/module is offered
2