Problem Decomposition and the Learning of Skills

One dimension of "divide and conquer" in problem solving concerns the domain and its subdomains. Humans learn the general structure of a domain while solving particular learning problems in it. Another dimension concerns the solver's goals and subgoals. Finding good decompositions is a major AI tactic both for defusing the combinatorial explosion and for ensuring a transparent end-product. In machine learning, pre-occupation with free-standing performance has led to comparative neglect of this resource, illustrated under the following headings. 1. Automatic manufacture of new attributes from primitives ("constructive induction"). 2. Machine learning within goal-subgoal hierarchies ("structured induction"). 3. Reconstruction of skills from human performance data ("behavioural cloning").

[1]  Claude E. Shannon,et al.  Computers and Automata , 1953, Proceedings of the IRE.

[2]  Randolph M. Jones,et al.  A symbolic solution to intelligent real-time control , 1993, Robotics Auton. Syst..

[3]  A. Newell.  Unified Theories of Cognition , 1990 .

[4]  Donald Michie.  New Commercial Opportunities Using Information Technology , 1989, Wissensbasierte Systeme.

[5]  Alen D. Shapiro,et al.  Structured induction in expert systems , 1987 .

[6]  Ivan Bratko,et al.  Reconstructing Human Skill with Machine Learning , 1994, ECAI.

[7]  Leon Sterling,et al.  The Art of Prolog , 1987, IEEE Expert.

[8]  Saso Dzeroski,et al.  Inductive Logic Programming: Techniques and Applications , 1993 .

[9]  John J. Grefenstette,et al.  Optimization of Control Parameters for Genetic Algorithms , 1986, IEEE Transactions on Systems, Man, and Cybernetics.

[10]  Peter D. Turney.  Cost-Sensitive Classification: Empirical Evaluation of a Hybrid Genetic Decision Tree Induction Algorithm , 1994, J. Artif. Intell. Res..

[11]  Claude Sammut,et al.  Learning to Fly , 1992, ML.

[12]  Stephen Muggleton,et al.  Efficient Induction of Logic Programs , 1990, ALT.

[13]  Stephen Muggleton,et al.  An Experimental Comparison of Human and Machine Learning Formalisms , 1989, ML.

[14]  Donald Michie,et al.  Man-Machine Co-operation on a Learning Task , 1969 .

[15]  Ryszard S. Michalski,et al.  Inductive inference of VL decision rules , 1977, SGAR.

[16]  M J Sternberg,et al.  Application of machine learning to structural molecular biology. , 1994, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[17]  Nils J. Nilsson,et al.  Reacting, Planning, and Learning in an Autonomous Agent , 1996, Machine Intelligence 14.

[18]  Donald Michie,et al.  Cognitive models from subcognitive skills , 1990 .