Department of Computer Science
Chair of Algorithm Engineering (Ls11)
Home Contact Deutsch English
Günter Rudolph: Lecture Introduction to Computational Intelligence (WS 2019/20)

Introduction to Computational Intelligence

(Wahlmodul INF-BSc-305 / AR-MSc-306)

Winter term 2019/20

Prof. Dr. Günter Rudolph

Wednesday 10:15 - 11:45 am Campus North, OH12, E.003
First Lecture: Wednesday, 09-Oct-2019

Tutorial: Marius Bommert (M.Sc.), LS 11 (web pages)

Instruction Language: English.
For a German version of this web page please click the 'Deutsch' button at the top right corner.

Written Exams:
  • 1st Exam Date: Thursday, 06-Feb-2020, 8:15am - 9:45am.
    Results of Exam: download (final version: 27-Feb-2020)
    Performance Record / Grading System
    Post Exam Review: Thursday, 27-Feb-2020, 11:30am - 12:30, OH 14, Room E04.

  • 2nd Exam Date:Monday, 15-June-2020, 1:00pm - 2:30pm. *** NEW ***

    Results of Exam: download (version: 03-July-2020)
    Performance Record / Grading System
    Post Exam Review: Thursday, 09-July-2020, starting 11:00am, OH 12, Room E.003. Registration required! Deadline: 08-July-2020, 11am. See email for details.

    Free attempt:This exam is a so-called free attempt, i.e., if you do not pass the exam it will not count as failure.

Typically, Computational Intelligence is used as an umbrella term for the fields of artificial neural nets (ANN), fuzzy systems (FS) and evolutionary computation (EC). This course offers a thorough introduction into all three fields.

Foundations of ANN: McCulloch-Pitts nets, perceptrons, Hopfield nets, supervised and unsupervised learning, backpropagation.
Foundations of FS: Fuzzy sets, fuzzy numbers, fuzzy logic, fuzzy reasoning.
Foundations of EC: Algorithmic basics, parameterization, analysis methods, limits of deployment.

Students should get an overview about the different aspects of Computational Intelligence. They should be familiar with the essential elements in all three fields (ANN, FS, EC) and able to deploy and adapt these methods for real applications. Moreover, they should be able to assess when to deploy these methods and when not.

09.10.19 Fuzzy Systems I  
16.10.19 Fuzzy Systems II  
23.10.19 Fuzzy Systems III  
30.10.19 Fuzzy Systems IV   (added new slide #34)
06.11.19 Fuzzy Systems V  
13.11.19 Evolutionary Algorithms I  
20.11.19 Evolutionary Algorithms II  
27.11.19 Evolutionary Algorithms III  
04.12.19 Evolutionary Algorithms IV  
11.12.19 Neural Networks I  
18.12.19 Neural Networks II  
08.01.20 Neural Networks III  
15.01.20 Neural Networks IV  
22.01.20 Neural Networks V   not relevant for exam

  • A.E. Eiben and J.E. Smith: Introduction to Evolutionary Algorithms. Corrected 2nd printing. Springer 2007.
  • Raul Rojas: Neural Networks - A Systematic Introduction. Springer 1996. Available online.
  • Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep Learning. MIT Press 2017.
  • G.J. Klir und B. Yuan: Fuzzy Sets and Fuzzy Logic. Prentice Hall 1995.
  • F. Höppner, F. Klawonn, R. Kruse und T. Runkler: Fuzzy Cluster Analysis. Wiley 1999.
  • Amit Konar: Computational Intelligence: Principles, Techniques and Applications. Springer 2005.

The university does not accept liability for the contents of linked external internet sites