A Novel Meta Learning System and Its Application to Optimization of Computing Agents' Results
Ondřej Kazı́k, Klára Pešková, Martin Pilát, Roman Neruda · 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology · 2012
We present a description of our multi-agent system where computational intelligence methods are embodied as software agents. This system is designed in order to allow easy experiments with learning, meta learning, gathering experience based on previous computations, and recommending suitable methods for particular data. The architecture of the system is presented and its meta learning abilities are demonstrated on a set of experiments with neural network models and both evolutionary and local search heuristics.