You are hereEducation

Education


Our teaching is closely related to our research and both are based on our vision on Computational Intelligence. The link between research and teaching is represented by the motivational scenarios for our main research threads concerning parameter setting in evolutionary algorithms, embodied evolution in robot swarms, and collective adaptation in populations of humans, smart devices, and robots. These scenarios provide inspiration for examples discussed during our classes and are used to define Master projects.

The CI staff is responsible for seven courses shown below.

Bachelor courses



  • Heuristics During this course students face a "real-life" situation: a problem is given without any hint regarding the applicable problem solving method. Student teams of 3 find or design an appropriate algorithm, implement it, and report on the obtained results.

  • Machine learning is the study of how to build computer systems that learn from experience. It is a very active subfield of Artificial Intelligence that intersects with statistics, cognitive science, information theory, and probability theory, among others. Over the last fifteen years, Machine Learning has gained immense importance for the design of search engines, robots, and sensor systems, and for the processing of large scientific data sets. This course presents the dominant concepts of machine learning methods including some theoretical background. We'll cover established machine learning techniques such as Decision Trees, Neural Networks, Bayesian Learning, Instance-based Learning and Support Vector Machines as well as some statistical techniques to assess and validate machine learning results.

  • Collective intelligence studies complex systems that spontaneously exhibit organised behaviour at the system level. This organised behaviour arises (emerges) from the interactions between many relatively simple components. There are numerous examples of such systems in nature and society, ranging from bird swarms and insect colonies to economy and social behaviour in people. In this course, students will learn to analyse a number of self-organising systems as well as apply algorithms inspired by these systems.


Master courses



  • Evolutionary Computing concerns computational methods based on Darwinian principles of evolution. It illustrates the usage of such methods as problem solvers and as simulation, respectively modelling tools. Students gain hands-on experience in performing experiments through a compulsory programming assignment.

  • Advanced Self-organizationThis course is about the understanding of the behavior and self-organization of systems in which the interaction of the components is not simply reducible to the properties of the components. The general question is: how should systems of many independent but interacting computational units cooperate in order to process information and achieve their goals?

  • Neural networks The course addresses key concepts and algorithms for pattern recognition and neural networks. It strives towards providing insight both from a theoretical perspective as well as more practical settings. In the end, the student should be able to confidently apply the aforementioned techniques in real-life settings and understand their theoretical basis. It covers a range of topics, including classification, regression, and clustering problems, elements of statistical pattern recognition, methods for estimation of probability distributions, linear classifiers, including Support Vector Machines, single-layer and multi-layer networks, RBF-networks and kernel methods, methods for dimensionality reduction, and methods for feature extraction and selection.

  • Data mining techniques The term “Big Data” is omnipresent nowadays. Data Mining Techniques are essential to make sense out of large datasets. The aim of the course is that students acquire data mining knowledge and skills that they can apply in a business environment. How the aims are to be achieved: Students will acquire knowledge and skills mainly through the following: an overview of the most common data mining algorithms and techniques (in lectures), a survey of typical and interesting data mining applications, and practical assignments to gain "hands on" experience. The application of skills in a business environment will be simulated through various assignments of the course.

  • Computational intelligence can be positioned as the research area that follows a bottom-up approach to developing systems that exhibit intelligent behavior in complex environments.Typically, sub-symbolic and nature-inspired methods are adopted that tolerate incomplete, imprecise and uncertain knowledge. This course covers nature-inspired techniques such as neural networks, evolutionary algorithms, and swarm intelligence as well as fuzzy systems. Special attention is paid to using such techniques for making autonomous and adaptive machines. N.B. This course is hosted by the UvA as part of the joint VU-UvA AI Masters.

Graduation projects

We offer a variety of graduation projects and of course we also welcome refreshing new ideas from the students. We maintain a high level of ambition for students who work on a CI related Master project. We strive for an outcome that is of significant scientific value, and therefore the Master project frequently leads to a publication of the work in the proceedings of a well-established international conference. Below you can find an overview of current graduation projects within our group, followed by a list of possible graduation projects. Feel free to contact any of the staff members in case you have question, or are interested in a graduation project within our group.

Current student projects (partial list)



  • Nicola Mularoni, Evolving robotic organisms in dynamic environments (supervisor: Guszti Eiben and Berend Weel)

  • David Los, Optimization of slab reheating (supervisor: Guszti Eiben)

  • Quintin Saijoen, Forming joint brains in robotic organisms by connecting echo state networks (supervisor: Guszti Eiben and Berend Weel)

  • Jan Bim, Fate-agent evolutionary algorithms in swarm robotics (supervisor: Guszti Eiben and Giorgios Karafotias)

  • Hassnae Belkasim, Data mining to improve forwarding of CRC patients from the GP (supervisor: Mark Hoogendoorn)

  • Marijn Lems, Analyzing Malicious Networks (supervisor: Evert Haasdijk)

  • Wessel Luijben,Forecasting future fitness - A smart restart strategy (supervisor: Zoltán Szlávik)

  • Danielle de Man, Evolving a Gene Regulatory Network (supervisor: Evert Haasdijk)

  • Diti Oudendag, Prediction of dairy farmer behavior under abolishment of the milk quota system (supervisor: Mark Hoogendoorn)

  • Nicolaas Nobel, Analysis of hotel reviews (supervisor: Mark Hoogendoorn)

Ideas for graduation projects

Supervisor: Evert Haasdijk

For many of us, “artificial intelligence” is something we find in fictitious adversaries in computer games like Call of Duty or Doom. But what if these adversaries could learn? If they were truly intelligent and could adapt to your playing style, learn to use terrain, etc. This is exactly the kind of adaptivity that I try to develop in my research - not in game settings, but in distributed systems such as a group of robots or software agents.

If you’re interested in doing a mini master, literature research or individual research project into such adaptive systems, feel free to contact me.
My aim is always to have students do meaningful projects: projects that involve you in real research, usually aiming at a proper scientific publication, not just a report that you get a grade on.


  • Curiosity as a driver for robust adaptive behaviour in robots

  • Distributed collective control in multi-module robots

  • Combining objective-free adaptation and task-driven learning

  • Self-configuring distributed evolution

  • Temporal sensori-motor clustering to handle dynamic environments

  • Scaleable modular differentiation and HyperNEAT in modular robots

Supervisor: Mark Hoogendoorn

In my research I mainly look at systems that are able to learn: this learning could either take place by looking at a huge database and discovering interesting patterns (i.e. data mining), but might also be the result of an interaction with a certain environment, which could be a physical environment, but also a human with which interaction takes place. For the former, an example is for instance a database of thousands of cancer patients, and trying to find novel relationships between the information about these patients that could improve the diagnosis as well as their treatment. For the latter, it might be a robot that should learn how to drive around in an unknown environment. If you are interested in these kinds of learning, please have a look at the example projects below, and of course feel free to create your own ideas as well!


  • eHealth: (1) Improvement of decision models for cancer using data mining; (2) Adaptive assistive agents that adapt their behavior based upon interaction with humans

  • Robotics: (1) The difference between online and off-line learning; (2) How can robots learn when to form aggregated organisms and when to stay alone in an unknown world?

  • Parameter Control in Evolutionary Algorithms: Learning how to control the parameters of an evolutionary algorithm on the fly.

  • RoboCup and Poker: (1) Can soccer players be evolved using co-evolution? ; (2) Can an adaptive automated poker player be developed that learns opponent strategies?

Partial list of past student projects


  • John Müller – Forensic data mining, 2012 (supervisor: Guszti Eiben)

  • Yoeri Staal – Highway Platooning Strategies, 2012 (supervisor: Willem van Willigen and Guszti Eiben)

  • Vincent Hoekstra – Predicting football results with an evolutionary ensemble classi er, 2012 (supervisor: Guszti Eiben)

  • Ruben Balk – A Semi-Distributed Evolutionary Algorithm With Fate Agents, 2012 (supervisor: Guszti Eiben and Selmar Smit)

  • Asparuh Hristov – Data mining to improve advertising revenue on the web, 2012 (supervisor: Mark Hoogendoorn)

  • Joost Huizinga, Evolving Robotic Organisms, 2012 (supervisor: Evert Haasdijk)

  • Covlescu Iulian Mihai, Investigating hotel bookings review score effects, 2012 (supervisor: Zoltán Szlávik)

  • Richard Koopmanschap – Learning expert knowledge in cognitive models, 2012 (supervisor: Mark Hoogendoorn)

  • Iuliana Manole, Try-on eyewear: serious gaming for opticians, 2012 (supervisor: Zoltán Szlávik)

  • Koen Pasman, Data Mining to detect Temporal Features in Video, 2012 (supervisor: Evert Haasdijk)

  • Astrid van der Poel, TV quality improvement in Telecommunications - Network Optimisation, Tele2, 2012 (supervisor: Zoltán Szlávik)

  • Joris de Ruiter, GENDER DIFFERENCES IN MUSICAL INTERESTS ON FACEBOOK, 2012

  • Rachid Siallioui, On-line evolution of robot controllers by an island evolution approach, 2012 (supervisor: Evert Haasdijk)

  • Niek Siekman, Real-time event recommendation using Twitter data, 2012 (supervisor: Zoltán Szlávik)

  • Leszek Ślażyński, Parallel Algorithms for Reservoir Computing with Diverse Spiking Neurons, 2012 (supervisor: Zoltán Szlávik)

  • Peter Tessel, Forecasting demand to improve the distribution of cars within Car2go, 2012 (supervisor: Zoltán Szlávik)

  • Armon Toubman – Adaptieve autonomy using trust models, 2012 (supervisor: Mark Hoogendoorn)

  • Matthijs Tolkamp, Neuro-Evolution of Robot Controllers with a Changing Robot Population on a Gathering and Collective Construction Task, Graduation year: 2012 (supervisor: Evert Haasdijk)

  • Vincent D. Warmerdam, Confusion Matrix Reweighting, 2012 (supervisor: Zoltán Szlávik)

  • Victor Anchidin, Information Enrichment of POIs using GPS trace data, 2011 (supervisor: Zoltán Szlávik)

  • Marina Boia, POI extraction from crawled content, 2011 (supervisor: Zoltán Szlávik)

  • Robert Gilaard, Data Mining - On Airline Passengers Reservations, 2011 (supervisor: Zoltán Szlávik)

  • Manisha Hiralall, Personalized product recommendations - De Online Drogist, 2011 (supervisor: Zoltán Szlávik)

  • Gabriel Mititelu, Outlier Detection and Forecasting in the context of the Floodcontrol Project, 2011 (supervisor: Zoltán Szlávik)

  • Andrei A. Rusu, Decoding Neural Representations of People and Personality Traits Using fMRI Multi-Voxel Pattern Analysis, 2011 (supervisor: Zoltán Szlávik)

  • Tim Stokman, Constraint conditional models for NLP applications, 2011 (supervisor: Guszti Eiben)

  • Robert-Jan Huijsman, An Investigation Into Evolving Distributed Systems, 2011 (supervisor: Guszti Eiben and Maarten van Steen)

  • Berend Weel, Emergence of Multi-Robot Organisms using On-line On-board Evolution, 2011 (supervisor: Guszti Eiben and Evert Haasdijk)

  • Said Ait Haddou Ou Ali, Optimization of economic fuelling for the Fokker 70/100, 2010 (supervisor: Zoltán Szlávik)

  • Arif Atta-ul-Quyyam, Speeding up MuPlusOne, 2010 (supervisor: Evert Haasdijk)

  • Seyoum Bekele, Maximizing Revenue in Transaction Banking ABN AMRO Bank, 2010 (supervisor: Zoltán Szlávik)

  • Thom Eijken, Bayesian Network Based Anomaly Detection in General Ledgers, 2010 (supervisor: Zoltán Szlávik)

  • Maarten IJlstra, Implementing an optimized data analysis to validate ad impressions, 2010 (supervisor: Zoltán Szlávik)

  • Georgios Karafotias, Evolutionary swarm robotics: encapsulated and distributed schemes, 2010 (supervisor: Guszti Eiben and Evert Haasdijk)

  • Dimitar Nedev, Co-evolving substrate layout in HyperNEAT, 2010 (supervisor: Evert Haasdijk)

  • Charalambos Paschalides, Extracting Trending Topics from Status Messages of Users of a Social Networking Site, 2010 (supervisor: Zoltán Szlávik)