2010 | OriginalPaper | Buchkapitel
Learning Cellular Automata Rules for Pattern Reconstruction Task
verfasst von : Anna Piwonska, Franciszek Seredynski
Erschienen in: Simulated Evolution and Learning
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper presents results of experiments concerning the scalability of two-dimensional cellular automata rules in pattern reconstruction task. The proposed cellular automata based algorithm runs in two phases: the learning phase and the normal operating phase. The learning phase is conducted with use of a genetic algorithm and its aim is to discover efficient cellular automata rules. A real quality of discovered rules is tested in the normal operating phase. Experiments show a very good performance of discovered rules in solving the reconstruction task.