Plenary talks

Researchers in robotics, natural language, and human cooperative behavior have proposed that some abstract theories relevant to cognitive activity are encoded genetically in humans. The biological advantages of this are (1) to reduce the learning time for acquisition of specific contextual models (e.g., from a language community; appropriate physics, etc.), and (2) to allow the determination of true statements about the world beyond those immediately available from direct experience. We believe that this hypothesis is a strong paradigm for the autonomous mental development of artificial cognitive agents and we give specific examples in cyber-physical systems and propose a theoretical and experimental framework for this. In particular, we show that knowledge and exploitation of symmetry theory aids in conceptualization of sensor data and can lead to greatly reduced reinforcement learning times on a selected set of problems and allows for the autonomous mental development of cognitive agents.