Abstract
Heuristics learning is defined as the process of discovering rules for how to apply problem solving operators. An analysis of transfer of training with respect to problem solving heuristics results in two transfer mechanisms; one based on the interplay between conjectures and refutations, and one based on the partitioning of a goal into independently realizable parts or subgoals. First, rules called proposers produce suggestions about which operator(s) should be considered in the current situation, while other rules — called censors — refute those suggestions which previous experience has shown to be bad. A system which can learn proposers and censors can grow by the successive attenuation of the conditions on the proposers and through the successive addition of censors. In the long run, such a system will apply each problem solving operator when and only when it is appropriate. Second, subgoaling rules encode knowledge of which parts of a goal description can be attained separately. Such rules can be learned by noticing the successive transformations of the current state during problem solving; each step which makes the current state more similar to the goal state defines a potential future subgoal. Subgoaling rules learned while solving one task can facilitate the solution to another task, if the tasks share at least one subgoal. A computer program is written on the basis of this theory, and shown to be able to transfer within a simple task domain.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Anderson JR (1983). The architecture of cognition. Cambridge, MA: Harvard University Press Anderson JR (1986). Knowledge compilation: The general learning mechanism. In Michalski RS, Carbonell JG, Mitchëll TM (eds.), Machine learning: An artificial intelligence approach (Vol II). Los Altos, CA: Kaufmann
Anderson JR, Farreli R, Sauers R (1985). Learning to program in LISP. Cognitive Science, 8, 87–129
Anzai Y, Simon HA (1979). The theory of learning by doing. Psychological Review, 124–140
Bratko I, Nisblett T (1979). Conjectures and refutations in a framework for chess endgame knowledge. In Michie D (ed.), Expert systems in the micro-electronic age. Edinburgh: The University Press
Davis R, King J (1976). An overview of production systems. In Elcock EW, Michie M (eds.), Machine Intelligence (Vol 8). New York: Wiley
Ernst GW, Newell A (1969). GPS: A case study in generality and problem solving. New York: Academic Press
Hovland CI (1951). Human learning and retention. In Stevens SS (ed.), Handbook of experimental psychology. New York: Wiley
Hunt EB, Poltrock SE (1974). The mechanics of thought. In Kantowit BH (ed.), Human information processing. New York: Wiley
Klahr D, Langley P, Neches R (eds.) (1987). Production system models of learning and development. Cambridge, MA: MIT Press
Lakatos I (1976). Proofs and refutations. Cambridge, MA: The University Press
Langley P (1982). Strategy acquisition governed by experimentation. Proceedings of the European Conference on Artificial Intelligence, Paris
Langley P (1983). Learning search strategies through discrimination. International Journal of Man-Machine Studies, 18, 513–541
Langley P (1985). Learning to search: From weak methods to domain-specific heuristics. Cognitive Science, 9, 217–260
Langley P, Ohlsson S, Thibadeau R, Walter R (1984). Cognitive architectures and principles of behavior. Proceedings of the Sixth Conference of the Cognitive Science Society, Boulder, Colorado
Luchins AS (1942). Mechanization in problem solving: The effect of Einstellung. Psychological Monographs, 248
Michalski RS, Carbonell JG, Mitchell TM (eds.). (1983). Machine learning. Palo Alto, CA: Tioga
Michalski RS, Carbonell JG, Mitchell TM (eds.) (1986). Machine Learning (Vol II). Los Altos, CA: Kaufmann
Mitchell TM (1977). Version spaces: A candidate elimination approach to rule learning. Proceedings of the Fifth International Joint Conference on Artificial Intelligence, pp 305–310
Mitchell TM, Utgoff PE, Banerji R (1983). Learning by experimentation: Acquiring and refining problem-solving heuristics. In Michalski RS, Carbonell JG, Mitchell TM (eds.), Machine learning: An artificial intelligence approach. Palo Alto, CA: Tioga, pp 163–190
Mitchell TM, Utgoff PE, Nudel B, Banerji R (1981). Learning problem-solving heuristics through practice. Proceedings of the International Joint Conference on Artificial Intelligence, Vancouver
Nason R (1986). A production system analysis of young children’ number development between the ages of two to eight years. Unpublished doctoral disseretation, Deakin University, Victoria, Australia
Newell A, Rosenbloom P (1981). Mechanisms of skill acquisistion and the law of practice. In Anderson JR (ed), Cognitive skills and their acquisition. Hillsdale, NJ: Erlbaum
Newell A, Simon HA (1963). GPS: A program that simulates human thought. In Feigenbaum EA, Feldman D (eds.), Computers and thought. New York: McGraw-Hill
Newell A, Simon HA (1972). Human problem solving. Englewood Cliffs, NJ: Prentice-Hall
Ohlsson S (1979). PSS3 reference manual (Report # 4). Working Papers from the Cognitive Seminar, Department of Psychology, University of Stockholm
Ohlsson S (1982). On the automated learning of problem solving rules. In Trapp R (ed.), Cybernetics and systems research. Amsterdam: North-Holland
Ohlsson S (1983). A constrained mechanism for procedural learning. Proceedings of the Eighth International Joint Conference on Artificial Intelligence pp 426–428. Karlsruhe
Ohlsson S (1984). Induced strategy shifts in spatial reasoning. Acta Psychologica, 57, pp 47–67
Ohlsson S (1986). Rational learning and intelligent tutoring systems. Proceedings of the Tenth World Computer Congress. Dublin, Ireland
Ohlsson S (1987). Truth vs. appropriateness. In Klahr D, Langley P, Neches R (eds.), Adaptive production system models of learning and development
Popper KR (1969). Conjectures and refutations. London: Routledge and Kegan
Paul Rosenbloom PS, Newell A (1986). The chunking of goal hierarchies: A generalized model of practice. In Michalski RS, Carbonell JG, Mitchell TM (eds.), Machine learning: An artificial intelligence approach (Vol II). Los Altos, CA: Kaufmann
Toulmin S (1972). Human understanding (Vol 1). Oxford: Clarendon Press
Vere SA (1978). Inductive learning of relational productions. In Waterman DA, Hayes-Roth F (eds.), Pattern-directed inference systems. New York: Academic Press
Young RM (1979). Production systems for modeling human cognition. In Michie D (ed.), Expert systems in the micro-electronic age. Edinburgh: The University Press
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1987 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ohlsson, S. (1987). Transfer of Training in Procedural Learning A Matter of Conjectures and Refutations?. In: Bolc, L. (eds) Computational Models of Learning. Symbolic Computation. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-82742-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-82742-6_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-82744-0
Online ISBN: 978-3-642-82742-6
eBook Packages: Springer Book Archive