Abstract
Previous attempts to model physics problem solving prompted me to focus on learning. How does a novice increase his or her competence, how does an expert adapts his or her knowledge to solve new problems? How does a novice becomes an expert? The sections below present the different paradigms developed in artificial intelligence to model learning, describe a system, and then provide an example describing how the system solves problems. Our system is a classifier system that builds up its knowledge by induction and finally solves physics problems. Classifier systems are a kind of rule based system in which rules act in parallel and are created by the use of a genetic algorithm. We added learning operators more compatible with human learning to the genetic algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Atkinson, J.: An Introduction to Motivation. Princeton: Van Nostrand 1964.
Blondin, C.: Towards Expertise in Hydrodynamics: Psychological Data. In this volume.
Belew, R.K. and Guerrity, M.: Back Propagation for the Classifier System, In: Proceedings of the third International Conference on Genetic Algorithms (J.D. Shaffer ed.), pp. 275–281. San Mateo, Cal.: Morgan Kaufmann 1989.
Booker, L.B.: Triggered Rule Discovery in Classifier Systems. In: Proceedings of the Third International Conference on Genetic Algorithms (J.D. Shaffer, ed.), pp. 265–274, 1989.
Booker, L.B., Goldberg, D.E. and Holland, J.H.: Classifier Systems and Genetic Algorithms. Artificial Intelligence, 40, 1-3, 235–282 (1989).
Carbonell, J.G.: Introduction: Paradigms for Machine Learning. Artificial Intelligence, 40, 1-3, 1–9 (1989).
Chalmers, D.: The Evolution of Learning: An Experiment in Genetic Connectionism. CRCC Technical Report 47, Indiana University (1990).
Davis, L.: Adapting Operator Probabilities In Genetic Algorithms. In: Proceedings of the Third International Conference on Genetic Algorithms (J.D. Shaffer, ed.), pp. 61–69, 1989.
Defays, D.: L’esprit en friche. Brussel: Mardaga 1987.
Fogarty, T.C.: Varying the Probability of Mutation in the Genetic Algorithm. In: Proceedings of the third International Conference on Genetic Algorithms (J.D. Shaffer, ed.), pp. 104–109, 1989.
Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Reading, Mass.: Addison-Wesley 1989.
Goldberg, D.E. and Richardson, J.: Genetic Algorithms with Sharing for Multimodal Function Optimisation. Genetic Algorithms and their Applications. In: Proceedings of an International Conference on Genetic Algorithms, pp. 41-49, 1987.
Hoffmeister, F. and Bäck, T.: Genetic Algorithms and Evolution Strategies: Similarities and Differences. In: Parallel Problem Solving from Nature (H.-P. Schwefel, R. Männer, eds.), Lecture Notes in Computer Science, Vol. 496, pp. 455–469. Berlin: Springer-Verlag 1991.
Holland, J.H., Holyoak, K.J., Nisbett, R.E. and Thagard, P.R.: Induction: Processes of Inference, Learning and Discovery. Cambridge, Mass.: MIT Press 1986.
Riolo, R.L.: Empirical Studies of Default Hierarchies and Sequences of Rules in Learning Classifier Systems. University of Michigan: Ann Arbor 1988.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sougné, J. (1993). Modelling of Physics Problem Solving with Classifier Systems. In: Caillot, M. (eds) Learning Electricity and Electronics with Advanced Educational Technology. NATO ASI Series, vol 115. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-02878-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-662-02878-0_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08157-6
Online ISBN: 978-3-662-02878-0
eBook Packages: Springer Book Archive