Towards basic level categories in cognitive agents

Cognitive agents seem to be a perfect fit to computational solutions capable of making sense of large datasets and facilitating interaction with human users. Following cognitive computing paradigm we present an approach towards modelling category-based organisation of agent's semantic memory. As such, we investigate the process of formation and utilization of basic level categories in autonomous systems. We provide a detailed description of internal organisation of agent's semantic memory inspired by results from cognitive science. In particular, we focus on providing a concise description of a preliminary computational model (proof of concept's implementation) for establishing basic level categories on top of data clusterization process. Finally, we test the presented approach against a real bird species dataset, and in comparison to other cluster analysis techniques.