Integrated course, 5.00 ECTS
Deep Learning deals with principles and models of how computers learn to understand the real world through hierarchies of interconnected concepts. Machine learning (ML) as a subdiscipline focuses on identifying specific "patterns" in raw data of individual domain domains. The goal is to support complex decision-making processes with the help of computers. Students understand concepts and process models of ML and are able to identify application areas for ML in various subject domains. They are able to efficiently use innovative learning algorithms (e.g., supervised or unsupervised learning algorithms) and to augment or adapt ML algorithms. Students understand the holistic process of ML experiments, starting with problem definition, acquiring data, analyzing and prioritizing data, preparing data, modeling, creating the learning architecture, including the selection of appropriate ML algorithms, model evaluation, and interpretation of results.
The graduate gains detailed knowledge of all aspects of the practical application of Computational Intelligence.
Recommended or required reading and other learning resources / tools
Books: Deep Learning (Adaptive Computation and Machine Learning). Ian Goodfellow und Yoshua Bengio, The Mit Press, 2016
Introduction to Machine Learning with Python: A Guide for Data Scientists. Sarah Guido, O'Reilly UK Ltd, 2016
Pattern Recognition and Machine Learning (Information Science and Statistics). Christopher M. Bishop, 2007
Understanding Machine Learning: From Theory to Algorithms. Shai Shalev-Shwartz und Shai Ben-David, Cambridge University Press, 2014
Mode of delivery
2 THW Lecture, 1 THW Tutorial
Prerequisites and co-requisites
Assessment methods and criteria
Lecture: final exam, Tutorial: continuous appraisal