A theory of intelligent systems

The author proposes a theoretical model consisting of seven basic elements: actuators, sensors, sensory processing, world modeling, task decomposition, value judgment, and global memory/communications. These elements are integrated into a hierarchical system architecture wherein (a) control bandwidth decreases about an order of magnitude at each higher level, (b) perceptual resolution of spatial and temporal patterns contracts about an order of magnitude at each higher level, (c) goals expand in scope and planning horizons expand in space and time about an order of magnitude at each higher level, and (d) world models and event memories expand in space and time by about an order of magnitude at each higher level. At each level, tightly coupled functional modules perform task decomposition, world modeling, sensory processing, and value judgment. Feedback control loops are closed at every level.<
>