Meta Learning in Multi-agent Systems for Data Mining

Ondrej Kazík, Klára Pesková, Martin Pilát, Roman Neruda

Abstract: In this paper we present the Pikater multi-agent system designed for solving complex data mining tasks. We emphasize the unique intelligent features of the system -- its ability to search the parameter space of the data mining methods to find the optimal configuration, and meta learning -- finding the best possible method for the given data based on the ontological compatibility of datasets.