Contributor(s)The Pennsylvania State University CiteSeerX Archives
Full recordShow full item record
AbstractIn this paper, we present the homogeneous architecture and distributed algorithms of an implemented system called NeuSter. Several sub-systems provide online learning for networks of million neurons on machine clusters. Our model unifies perception and action for autonomous robot controlling. NeuSter extracts information from sensors, builds its own representations of the environment in order to learn non predefined goals.