Information on individual educational components (ECTS-Course descriptions) per semester

Basics in statistics, probability theory and linear algebra. 

Learning from examples is not exclusively restricted to living things. In fact, it is nowadays the basic principle used in a huge number of exciting applications, which rely on algorithms that are no longer explicitly defined but use data to learn how to behave. In this course the principles of such algorithms and methods are covered:

• concepts and differences of supervised-learning and unsupervised-learning
• dimensionality reduction (feature extraction, feature selection, curse of dimensionality)
• clustering (k-means, gaussian mixture models)
• classification and regression (SVM, Bayes, knn, decision trees, boosting, neural networks)
• The machine learning prozess (cross-validation, data pre-processing, significance tests)

The methods are implemented or applied by using python with frameworks such as scikit-learn, numpy and keras. 

Students are able to

• describe the conceptual differences between supervised- and unsupervised-learning
• explain how computers can be used to solve problems without explicitly programming them do to so
• select appropriate methods for a given problem
• interpret and utilize the results of the learned methods
• compare different methods with regards to accuracy and robustness 
• solve problems with methods from machine learning

Lectures and exercises in homework. 

Final exam (75%), evaluation of exercises (25%). 

For a positive grade, a minimum of 50% of the possible points must be achieved in each part of the examination.

 None

• Bishop, Christopher (2016): Pattern Recognition and Machine Learning. Springer
• Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron (2016): Deep Learning. MIT Press. Available at: URL: https://www.deeplearningbook.org/
• Mitchell, Tom (2017): Machine Learning. Available at: URL: http://www.cs.cmu.edu/~tom/NewChapters.html
• Norvig, Peter; Russel, Stuart (2021): Artificial Intelligence: A Modern Approach, Global Edition.

Face-to-face event with recording of the lecture