Data Science and Artificial Intelligence

Computational Intelligence 2

Integrated course, 10.00 ECTS

 

Course content

Students acquire in-depth knowledge of artificial neural networks, evolutionary methods, swarm intelligence, artificial immune systems, fuzzy systems and associated probability techniques with regard to detailed mathematical foundations and principles and the algorithms derived from them. The associated transformation of these algorithms to computer-aided tools determines the methodological competence of the students. They are able to design and execute CI experiments holistically and on demand, and students can choose the appropriate process models and tools. Students are able to evaluate and interpret results of a CI experiment based on clearly defined criteria.

Learning outcomes

The graduate possesses detailed advanced knowledge of Computational Intelligence.

Recommended or required reading and other learning resources / tools

Books: Computational Intelligence: Concepts to Implementations. Russell C. Eberhart, Yuhui Shi, Morgan Kaufmann, 2014
Computational Intelligence: Methods and Techniques. Leszek Rutkowski, Springer, 2010
Handbook of Swarm Intelligence: Concepts, Principles and Applications. Bijaya Ketan Panigrahi, Yuhui Shi, Meng-Hiot Lim, Springer Science & Business Media, 2011
Artificial Intelligence: A Modern Approach. Stuart Russell und Peter Norvig, Addison Wesley, 2016
Journals:

Mode of delivery

2,5 THW Lecture, 2,5 THW Tutorial

Prerequisites and co-requisites

Modules AI 1 and MAT 1

Assessment methods and criteria

Lecture: final exam, Tutorial: continuous appraisal + project work