CHAIR OF

COMPUTATIONAL

INTELLIGENCE

++ News: The exam review will take place on April 5 from 10:00 to 12:00 in Room G29-018 +++

Description

This course provides in-depth knowledge about swarm intelligence in technical systems. In swarm intelligence, we deal with a group of simple and usually homogenous individuals with simple rules. Usually, swarms can achieve a complex and intelligent behaviour using local interactions between its members. This collective property can be used in technical systems.. One advanced application of swarm intelligence is in swarm robotics, in which simple small robots can collectively learn to achieve some predefined complex tasks. During this course, the algorithms of swarm intelligence are presented, analysed and compared. The following topics will be covered:

Part 1: Fundamentals of swarm intelligence

• Swarm stability and stability analysis
• Swarm aggregation
• Swarm in known environments
• Swarm in unknown environments: Particle Swarm Optimization
• Dynamic Optimization
• Multi-Objective Particle Swarm Optimization 

Part 2: Swarm and multiagent systems

• Division of labour and task allocation
• Swarm clustering and sorting
• Ant systems and optimization

Part 3: Applications

• Swarm localization and display
• Swarm robotics

Lecturer

• Sanaz Mostaghim (Course)
• Sebastian Mai (Tutorials)

Lectures:

This lecture will take place in presence format in Thursdays 3.15 pm to 4.45 pm in room G29-307. We will record the lectures and upload them online on Mediasite. 

Slides

• Chapter 1: Organization and Introduction
• Chapter 2 (part 1): Swarm Aggregation
• Chapter 2 (part 2): Swarms in Known Environments, Emergence and Entropy
• Chapter 3 (part 1): Swarms in unknown environments: Optimization algorithms 
• Chapter 3 (part 2): Multi-Objective Particle Swarm Optimization 
• Chapter 4 (part 1): Ant Systems: Sorting and Division of Labour
• Chapter 4 (part 2): Ant systems: Ant Colony Optimization
• Chapter: Collective Decision-making
• Chapter 5: Swarm Robotics
• Chapter 6: Swarm Localization 

Recorded lectures

Please refer to https://mediasite.ovgu.de/Mediasite/Channel/549520847511475391c7c27f9930ddee5f/browse/null/most-recent/null/0/326a7500a5454a2ea8612fb622f518e314  for the recorded lectures. Note: Here you must log in with your URZ account, otherwise the list of videos is empty. To log in, you have to click the button labelled "GU" and supply your URZ credentials. You may need to follow the link a second time after you completed the login procedure.

We will upload the recorded lectures after each lecture. 

Tutorials:

To meet the large demand for the swarm intelligence course, we offer a live tutorial in the lecture hall with explanations for solving the tutorials. Those tutorials will be recorded.

To register for the course in the elearning platform, please go to elearning.ovgu.de and register to the course "Swarm Intelligence". The enrolment key is the same as the password for the slides (please refer to the organization lecture).

Solve the assignments yourself (This is how you can maximize your learning experience!)

1. After solving each assignment, refer to the tutorial or the video-recorded explanation to check your results
2. Ask questions that you have during the tutorials or the forum in the elearning platform.

To be able to write the exam, you must fulfil the following criteria:

•  You have to pass a midterm exam. We will provide the details during the lectures.

Assignments

The assignments will be published during the semester.

For the programming exercises you can use google-colab if you want to avoid installing Jupyter on your own pc. Unfortunately, the visualization package is not fully supported, so you have to make your own visualization, e.g., with matplotlib.

• Sheet 1: 22. 10.
• Sheet 2: 29. 10. -- SI-Programming.ipynb
• Sheet 3: 05. 11.
• Sheet 4: 12. 11. -- no live tutorial (refer to the videos)
• Sheet 5: 19. 11.
• Sheet 6: 26. 11. + Questions and Answers for Sheets 1-5
• Midterm Exam: 03. 12. (No Exercise)
• Sheet 7: 10. 12.
• Sheet 8: 17. 12.
• Sheet 9: 14. 01.

Exams from past years

• Exam of WS 17/18 - annotated version
• Exam of WS16/17 - annotated version
• Exam of WS15/16 - annotated version
• Exam of WS14/15 - annotated version
• Exam of WS13/14

 Literature

• Veysel Gazi and Kevin M. Passino, Swarm Stability and Optimization, Springer, 2011
• Eric Bonabeau, Marco Dorigo and Guy Theraulaz, Swarm Intelligence: From Natural to Artificial Systems, Oxford University Press, 1999
• Andries Engelbrecht, Fundamentals of Computational Swarm Intelligence, Wiley 2006
• James Kennedy and Russel Eberhart, Swarm Intelligence, Morgan Kaufmann, 2001
• Zbigniew Michalewicz and David Fogel, How to solve it: Modern Heuristics, Springer, 2001
• Marco Dorigo and Thomas Stützle, Ant Colony Optimization, The MIT Press, 2004
• C. Solnon: Ant Colony Optimization and Constraint Programming. Wiley 2010
• Gerhard Weiss, Multiagent Systems: A modern approach to distributed artificial systems, The MIT Press, 2000
• Christian Müller-Schloer, Hartmut Schmeck and Theo Ungerer, Organic Computing A Paradigm Shift for Complex Systems, Springer, 2011