Analytical design of intelligent machines

Abstract

The problem of designing “intelligent machines” operating in uncertain environments with minimum supervision or interaction with a human operator is examined. The structure of an “intelligent machine” is defined to be the structure of a Hierarchically Intelligent Control System, composed of three levels hierarchically ordered according to the principle of “increasing precision with decreasing intelligence”, namely: the organizational level, performing general information processing tasks in association with a long-term memory, the coordination level, dealing with specific information processing tasks with a short-term memory, and the control level, which performs the execution of various tasks through hardware using feedback control methods. The behavior of such a machine may be managed by controls with special considerations and its “intelligence” is directly related to the derivation of a compatible measure that associates the intelligence of the higher levels with the concept of entropy, which is a sufficient analytic measure that unifies the treatment of all the levels of an “intelligent machine” as the mathematical problem of finding the right sequence of internal decisions and controls for a system structured in the order of intelligence and inverse order of precision such that it minimizes its total entropy. A case study on the automatic maintenance of a nuclear plant illustrates the proposed approach.