Biologically plausible hybrid network design and motor control

摘要

I outline a general theoretical framework for understanding the relationship between genetic algorithms and traditional learning methods on the one hand, and between symbolic and distributed information processing on the other. By way of example, I discuss aspects of motor control problems and describe a theoretical biologically plausible hybrid network inspired by the theoretical framework. Preliminary analysis suggests the net might be a useful point of departure for developing biologically plausible visually guided motor control systems.