Advanced Computerlab

Course content

The students

• remember and understand the basic tasks and method of mathematicl algorithms and their praktical appliastion
• are able to use mathematical programming tools
• are able to apply, analyze and implement mathematical algorithms
• are able to document and present mathematical algorithms

Advanced Computerlab Data Science

In the Advanced Computerlab Data Science, current machine learning models are implemented, trained, applied and interpreted in order to work on practical questions on the basis of extensive structured or unstructured data sets. Fundamentals and techniques imparted on a theoretical level (e.g. models and their evaluation, optimization algorithms, interpretation techniques) are applied and expanded in practice by means of functions provided in various frameworks (e.g. TensorFlow, Keras, Matplotlib). The independent implementation of machine learning models in Python forms a further focus in addition to the use of specialized frameworks.

Advanced Computerlab Statistical Learning 

The focus of the Advanced Computerlab Statistical Learning is on well-known machine learning methods. These are mainly considered from the perspective of mathematical statistics. For presented structured and unstructured data, students are taught how to find suitable solutions, how to implement them, e.g. in the statistical software R, and how to interpret the results. Advantages and disadvantages of the methods used as well as the underlying model assumptions are discussed from a probabilistic or statistical point of view. Students have the opportunity to apply their knowledge of probability theory and mathematical statistics acquired in previous courses. One focus of the course is the independent implementation of machine learning models using frameworks such as TensorFlow, mlr3, Keras, among others.