Abstract
Interest in psychological experimentation from the Artificial Intelligence community often takes the form of rigorous post-hoc evaluation of completed computer models. Through an example of our own collaborative research, we advocate a different view of how psychology and AI may be mutually relevant, and propose an integrated approach to the study of learning in humans and machines. We begin with the problem of learning appropriate indices for storing and retrieving information from memory. From a planning task perspective, the most useful indices may be those that predict potential problems and access relevant plans in memory, improving the planner's ability to predict and avoid planning failures. This “predictive features” hypothesis is then supported as a psychological claim, with results showing that such features offer an advantage in terms of the selectivity of reminding because they more distinctively characterize planning situations where differing plans are appropriate.
We present a specific case-based model of plan execution,Runner, along with its indices for recognizing when to select particular plans—appropriateness conditions—and how these predictive indices serve to enhance learning. We then discuss how this predictive features claim as implemented in theRunner model is then tested in a second set of psychological studies. The results show that learning appropriateness conditions results in greater success in recognizing when a past plan is in fact relevant in current processing, and produces more reliable recall of the related information. This form of collaboration has resulted in a unique integration of computational and empirical efforts to create a model of case-based learning.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Alterman, R. (1985). Adaptive planning: refitting old plans to new situations.Cognitive Science.
Anderson, J.R. (1990). TheAdaptive Character of Thought Hillsdale, NJ: Lawrence Erlbaum.
Berger, J., and Hammond, K. (1990). ROENTGEN: A case-based approach to radiation therapy planning. InThe Proceedings of the 32nd Annual Scientific Meeting of the American Society of Therapeutic Radiology and Oncology.
Berger, J., and Hammond, K.J. (1991). ROENTGEN: A memory-based approach to radiation therapy treatment design. In (R. Bareiss, Ed.),Proceedings of the 1991 DARPA Workshop on Case-Based Reasoning. Los Altos, CA: Morgan Kaufmann, Associates.
Birnbaum, L., and Collins, G. (1988). The transfer of the experience across planning domains through the acquisition of abstract strategies. In J. Kolodner (Ed.),Proceedings of a Workshop on Case-based Reasoning. Los Altos, CA: Morgan Kauffmann, p. 61–79.
Carbonell, J.G. (1983). Learning by analogy: Formulating and generalizing plans from past experience. In R.S. Michalski, J.G. Carbonell, and T.M. Mitchell (Eds.),Machine Learning: An Artificial Intelligence Approach. Los Altos, CA: Morgan Kaufman.
Dyer, M.G. (1983).In-depth understanding: A computer model of integrated processing for narrative comprehension. Cambridge, MA: MIT Press.
Feigenbaum, E. (1990). The simulation of verbal learning behavior. In J. Shavlik, and T. Dietterick (Eds.),Readings in Machine Learning. New York: Morgan Kauffmann.
Gentner, D. (1983). Structure-mapping: A theoretical framework for analogy.Cognitive Science, 7, 155–170.
Gentner, D., and Landers, R. (1985). Analogical reminding; A good match is hard to find. InProceedings of the International Conference on systems, Man, and Cybernetics. Tucson, AZ.
Gick, M.L., and Holyoak, K.J. (1980). Analogical problem solving.Cognitive Psychology, 12, 306–355.
Gick, M.L., and Holyoak, K.J. (1983). Schema induction and analogical transfer.Cognitive Psychology, 15, 1–38.
Hammond, K.J., Marks, M., and Converse, T. (1992). Planning, opportunism and memory. In D. Atkinson, and D. Miller (Eds.),Planning Systems for Autonomous Mobile Robots.
Hammond, K.J., Converse, T., and Martin, C. (1990). Integrating planning and acting in a case-based framework. InThe Proceedings of the 1990 National Conference of Artificial Intelligence.
Hammond, K. (1989).Case-based planning: Viewing planning as a memory task. San Diego: Academic Press, Inc.
Hammond, K.J., and Seifert, C.M. (1992). Indexing plans in memory.Proceedings of the Fourteenth Annual Cognitive Science Society Conference, Bloomington, IN.
Hammond, K.J., and Seifert, C.M. (1993) A cognitive science approach to case-based planning. In S. Chipman and A.L. Meyrowitz (Eds.),Foundations of Knowledge Acquisition: Cognitive Models of Complex Learning. Norwell, MA: Kluwer Academic Publishers, 245–267.
Hammond, K.J., Seifert, C.M., and Gray, K.C. (1991). Functionality in analogical transfer: A hard match is good to find.Journal of the Learning Sciences, 1:2, 111–152.
Johnson, H.M., and Seifert, C.M. (1992). The role of predictive features in retrieving analogical cases.Journal of Memory and Language, 31, 648–667.
Johnson, H.K., and Seifert, C.M. (1990). Predictive utility in case-based memory retrieval. InProceedings of the Twelfth Annual Cognitive Science Society, Boston, Massachusetts.
Kolodner, J.L., and Simpson, R.L. (1989). The mediator: Analysis of an early case-based problem.Cognitive Science.
Kolodner, J.L. (1984).Retrieval and organizational strategies in conceptual memory: A computer model. Hillsdale, NJ: Lawrence Erlbaum Associates.
Kolodner, J.L., Simpson, R.L., and Sycara, K. (1985). A process model of case-based reasoning in problem-solying. InThe Proceedings of the Ninth International Joint Conference on Artificial Intelligence, Los Angeles, CA: DCAI.
Kolodner, J. (1987). Extending Problem Solver Capabilities Through Case-Based Inference. InProceedings of the Fourth International Workshop on Machine Learning. Los Altos, CA: Morgan Kaufman Publishers, Inc., p. 167–178.
Kolodner, J.L. (1983). Reconstructive memory: A computer model.Cognitive Science, 7, 281–328.
Lehnert, W. (1980). Plot units and narrative summarization.Cognitive Science, 5, 293–331.
Martin, C.E. (1990). Direct Memory Access Parsing. Ph.D. Thesis, Yale University.
Martin, C.E., and Reisbeck, C. (1986). Uniform parsing and inferencing for learning. InProceedings of the Fifth Annual Conference on Artificial Intelligence, Philadelphia, PA: AAAI.
McDougal, T., Hammond, K.J., and Seifert, C.M. (1991). A functional perspective on reminding.Proceedings of the Thirteenth Annual Cognitive Science Society, Chicago, Illinois.
McDougal, T. and Hammond, K. (1992). A recognition model of geometry theorem-proving.Proceedings of the Fourteenth Annual Conference of the Cognitive Science Society, Bloomington, Indiana.
Minton, S. (1988). Learning Effective Search-Control Knowledge: An Explanation-Based Approach. Technical Report # 133, Carnegie-Mellon University, Department of Computer Science.
Newell, A. (1991).Unified theories of cognition. Cambridge: Harvard University Press.
Owens, C. (1990). Functional Criteria for Indices and Labels.Working Notes of the AAAI Spring Symposium Series. Palo Alto, CA.
Pazzani, M.J. (1989). Indexing Strategies for goal specific retrieval of cases.Proceedings of the Case-Based Reasoning Workshop, Pensacola Beach, FL.
Pazzani, M.J. (1991).Learning Causal Relationships: An integration of empirical and explanation-based learning methods. Hillsdale, NJ: Lawrence Erlbaum Associates.
Pirolli, P.L., and Anderson, J.R. (1985). The role of learning from examples in the acquisition of recursive programming skills.Canadian Journal of Psychology, 39, 240–272.
Ratterman, M.J., and Gentner, D. (1987). Analogy and similarity: Determinants of accessibility and inferential soundness. In J. Anderson (Ed.),Proceedings of the Ninth Annual Meeting of the Cognitive Science Society. Hillsdale, NJ: Lawrence Erlbaum Associates, Inc.
Riesbeck, C.K., and Schank, R.C. (1989).Inside Case-based Reasoning. Hillsdale, NJ: Erlbaum.
Rosenschein, S.J., and Kaelbling, L.P. (1986). The Synthesis of Digital Machines with Provable Epistemic Properties. InProceedings of 1986 Conference on Theoretical Aspects of Reasoning About Knowledge.
Ross, R.H. (1987). This is like that: The use of earlier problems and the separation of similarity effects.Journal of Experimental Psychology: Learning, Memory, and Cognition, 13, 629–639.
Ross, B.H. (1989). Distinguishing types of superficial similarities: Different effects on the access and use of earlier problems.Journal of Experimental Psychology: Learning, Memory, and Cognition, 15, 456–468.
Ross, B.H. (1989). Remindings in learning and instruction. In S. Vosniadou and A. Ortony (Eds.),Similarity and analogical reasoning. Cambridge: Cambridge University Press.
Schank, R.C. (1982).Dynamic memory: A theory of reminding and learning in computers and people. New York: Cambridge University Press.
Schank, R.C., and Abelson, R.P. (1977).Scripts, plans, goals, and understanding. Hillsdale, NJ: Lawrence Erlbaum Associates.
Schank, R.C., and Riesbeck, C. (1990).Inside case-based reasoning. Hillsdale, NJ: Erlbaum.
Seifert, C.M. (1988). Goals in Reminding.Proceedings of the DARPA Work on Case-based Reasoning in AI, Clearwater Beach, Florida.
Seifert, C.M. (1993) “The role of goals in analogical retrieval.” K.J. Holyoak and J.A. Barnden (Eds),Advances in Connectionist and Neural Computation Theory, Vol. 2: Analogical Connections. Norwood, NJ: Ablex Publishing Company.
Seifert, C.M. McKoon, G., Abelson, R.P., and Ratcliff, R. (1986). Memory connections between thematically similar episodes.Journal of Experimental Psychology: Learning, Memory, and Cognition, 12, 220–231.
Simpson, R.L. (1985). A Computer Model of Case-based Reasoning in Problem-solving: An Investigation in the Domain of Dispute Mediation. Ph.D. Thesis, School of Information and Computer Science, Georgia Institute of Technology.
Smith, E.E., and Medin, D.L. (1981).Categories and concepts. Cambridge, MA: Harvard University Press.
VanderStoep, S.W., and Seifert, C.M. (1993). “Learning ‘how’ vs. learning ‘when:’ Improving problem solving transformer.”Journal of the Learning Sciences.
Vanderstoep, S., and Seifert, C.M. (1993). “Learning WHEN: Predictive features in analogical transfer.” P. Pintrich, D. Brown, C. Weinstein (Eds.),Perspectives on Student Motivation, Cognition, and Learning: Essays in Honor of Wilbert J. McKeachie. Hillsdale, NJ: Erlbaum Associates.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Seifert, C.M., Hammond, K.J., Johnson, H.M. et al. Case-based learning: Predictive features in indexing. Mach Learn 16, 37–56 (1994). https://doi.org/10.1007/BF00993173
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00993173