Computational Intelligence is a research area within Artificial Intelligence opposing itself to the traditional, symbolic oriented, AI. The reason is that symbolic AI is applicable in formal defined domains such as chess, but not for every day problems such as vision, speech recognition, dealing with ambiguous data, natural language processing etc. New techniques and methods, inspired by nature were developed to tackle these problems. The techniques and methods include evolutionary computing, fuzzy computing, swarm intelligence, ant systems andneuro-computing.
The main difference is that classical artificial intelligence techniques are top-to-bottom where the structure of models, solutions, parameter settings are all imposed from above by the designer.
Computational intelligence techniques are in general bottom-up, where order and structure emerges from an unstructured beginning and is learned from data from, or interaction with, the environment.
Within HMI Computational Intelligent Techniques are used, among other things, in the development of Intelligent Embodied Agents situated in Virtual Environments, Conversational Agents and in Robot Soccer.
The following HMI-members are working on Computational Intelligence:Former HMI-members:
Here you can find the publications
Students can find information about assignments:
[ final project ] [ Capita selecta and Research Topics ] at our Msc webpages.