Computational Intelligence Group

Computational Intelligence is an approach to Artificial Intelligence roughly distinguished by its sub-symbolic, bottom-up character and the use of nature-inspired computational methods. We expect that the next wave of artificial intelligence will be collective intelligence, based on heterogeneous groups of many connected units, e.g., smart devices and robots. Furthermore, we envision two features becoming essential: adaptivity and autonomy.

We perceive collectivity, adaptivity, and autonomy as the Grand Challenges in intelligent systems of the future because these systems must be equipped for scenarios where the operational circumstances are:

• changing,
• not fully known in advance,
• so complex that behavioural rules cannot be designed & coded by traditional analytical approaches.

Our research addresses fundamental issues about how to design, use, and understand intelligent systems made up by autonomous machines that can self-organise, evolve, and learn. In particular, we work in evolutionary computing, machine learning and complex systems for optimization, modeling, robotics and sensory data processing (e.g., images or audio). The strategic lines of research of the group are:

• Models and algorithms for evolving and learning machines.
• Self-organization and evolution in robot swarms.
• Machine learning, and optimization techniques for non-differentiable complex systems.