Building symbolic representations of intuitive real-time skills from performance data

Real-time control skills are ordinarily tacit | their possessors cannot explicitly communicate them. But given su cient sampling of a trained expert's input{output behaviour, machine learning programs have been found capable of constructing rules which, when run as programs, deliver behaviours similar to those of the original exemplars. These `clones' are in e ect symbolic representations of subcognitive behaviours. After validation on simple pole-balancing tasks, the principles have been successfully generalized in ight-simulator experiments, both by Sammut and others at UNSW, and by Camacho at the Turing Institute. A ight plan switches control through a sequence of logically concurrent sets of reactive behaviours. Each set can be thought of as a committee of subpilots who are respectively specialized for rudder, elevators, rollers, thrust, etc. The chairman (the ight plan) knows only the mission sequence, and how to recognize the onset of each stage. This treatment is essentially that of the `blackboard model', augmented by machine learning to extract subpilot behaviours (seventy-two behaviours in Camacho's auto-pilot for a simulated F-16 combat plane). A `clean-up' e ect, rst noted in the polebalancing phase of this enquiry, results in auto-pilots which y the F-16 under tighter control than the human from whom the behavioural records were sampled. 385 REAL-TIME SKILLS Table 15.1. Criteria of strong and weak AI Strong Weak Feasibility Human-level intelligence Human-level intelligence of goals will be achieved in will be implemented only machines within in some unimaginable foreseeable time. future, or perhaps never. Forms of All thought can be Most thought is implemenmechanized as sequential intuitive, not tation logical reasoning from introspectable, axiomatic descriptions non-logical, associative, of the world. The approximate and `physical symbol system `fuzzy': best modelled hypothesis': all agents, by brain-like including intelligent, ultra-parallel networks. are best implemented symbolically. Personnel Vintage AI professionals, Members of other e.g. Turing, Simon, professions, particularly Newell, McCarthy, in linguistics, Feigenbaum, Nilsson, and neurobiology, physics, their followers. and philosophy.