The field of knowledge acquisition and machine learning is a rapidly expanding field of knowledge and the subject of numerous research and development projects. The acquisition of knowledge can take place in different ways. Thus a system can benefit from experiences already made, it can be trained, or it draws conclusions from extensive background knowledge.

The lecture covers symbolic learning methods such as inductive learning (learning from examples, learning by observation), deductive learning (explanation-based learning) and learning from analogies, as well as sub-symbolic techniques such as neural networks, support vector machines and genetic algorithms. The lecture introduces the basic principles and structures of learning systems and examines the algorithms developed so far. The structure and operation of learning systems is presented and explained with some examples, especially from the fields of robotics and image processing.

Learning obectives:

• Students acquire knowledge of the fundamental methods in the field of machine learning.
• Students can classify, formally describe and evaluate methods of machine learning.
• Students can use their knowledge to select suitable models and methods for selected problems in the field of of machine learning.

Die Foliensätze sind als PDF verfügbar

Weiterführende Literatur

• Artificial Intelligence: A Modern Approach - Peter Norvig and Stuart J. Russell
• Machine Learning - Tom Mitchell
• Pattern Recognition and Machine Learning - Christopher M. Bishop
• Reinforcement Learning: An Introduction - Richard S. Sutton and Andrew G. Barto
• Deep Learning - Ian Goodfellow, Yoshua Bengio, Aaron Courville

Weitere (spezifische) Literatur zu einzelnen Themen wird in der Vorlesung angegeben.