Task Structures: What To Learn?

Broadly characterized, learning can improve problem-solving performance by increasing its efficiency and effectiveness, and by improving the quality of produced solutions. Traditional AI systems have limited the role of learning to the first two performance-improvement goals. We have developed a reflection process that uses a model of the system’s functional architecture to monitor its performance, suggest a quite broad range of modifications when it fails, and subsequently perform these modifications to improve its problem-solving mechanism. The modifications suggested and performed by the reflection process may result in performance improvement of all the above types.

[1]  Eleni Stroulia,et al.  Functional representation and reasoning for reflective systems , 1995, Appl. Artif. Intell..

[2]  Ashok K. Goel,et al.  Integration of case-based reasoning and model-based reasoning for adaptive design problem-solving , 1989 .

[3]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[4]  Ashwin Ram,et al.  Introspective reasoning using meta-explanations for multistrategy learning , 1995 .

[5]  Gerald J. Sussman,et al.  A Computational Model of Skill Acquisition , 1973 .

[6]  William J. Clancey,et al.  Heuristic Classification , 1986, Artif. Intell..

[7]  Randall Davis,et al.  Interactive Transfer of Expertise: Acquisition of New Inference Rules , 1993, IJCAI.

[8]  Ashok K. Goel,et al.  An Experience-based Approach To Navigational Route Planning , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Kristian J. Hammond,et al.  Case-Based Planning: Viewing Planning as a Memory Task , 1989 .

[10]  R. Wilensky.  Planning and Understanding: A Computational Approach to Human Reasoning , 1983 .

[11]  Steven Minton,et al.  Quantitative Results Concerning the Utility of Explanation-based Learning , 1988, Artif. Intell..

[12]  Luc Steels,et al.  Components of Expertise , 1990, AI Mag..

[13]  Bob J. Wielinga,et al.  KADS: a modelling approach to knowledge engineering , 1992 .

[14]  Dean Allemang,et al.  Understanding programs as devices , 1990 .

[15]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[16]  John McDermott,et al.  Preliminary steps toward a taxonomy of problem-solving methods , 1993 .

[17]  Kathy A. Johnson.  Exploiting a functional model of problem solving for error detection in tutoring , 1993 .

[18]  Daniel R. Kuokka,et al.  The deliberative integration of planning, execution, and learning , 1990 .

[19]  Ryszard S. Michalski,et al.  Machine learning: an artificial intelligence approach volume III , 1990 .

[20]  John S. Gero,et al.  Behaviour: A link between function and structure in design , 1992 .

[21]  Tom M. Mitchell,et al.  Learning Problem-Solving Heuristics Through Practice , 1981, IJCAI.

[22]  Michael Freed,et al.  Reasoning about performance intentions , 1992 .

[23]  M. Weintraub.  An explanation-based approach to assigning credit , 1991 .

[24]  Ashok K. Goel,et al.  Representation, organization, and use of topographic models of physical spaces for route planning , 1991, [1991] Proceedings. The Seventh IEEE Conference on Artificial Intelligence Application.

[25]  Jaime G. Carbonell,et al.  Derivational analogy: a theory of reconstructive problem solving and expertise acquisition , 1993 .

[26]  Ashok K. Goel,et al.  Generic Teleological Mechanisms and their Use in Case Adaptation , 1992 .