Abstract
Almost all approaches to learning by analogy concentrate on what I will call predictive analogy, namely the process of inferring further similarities between two objects given some existing similarities. While the role of predictive analogy as a general purpose learning heuristic is rather dubious, a point I will make briefly in this paper, there is another mode of analogy—namely the process ofcreating similarities between two objects where none existed before, and which I will refer to as interpretive analogy—that aids learning in much more significant ways. However, the process underlying interpretive analogy has not been properly addressed yet. In this paper I introduce this mode of analogy, discuss its role in learning, and present an algebraic approach to formalizing the underlying process.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Carpenter G.A. and Grossberg S., 1987, “A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine,”Computer Vision, Graphics and Image Processing 37, pp. 54–115.
Cohn P.M., 1981,Universal Algebra, revised edition, D. Reidel, Dordrecht, Holland.
Gordon W.J.J., 1961,Synectics: The Development of Creative Capacity, Harper & Row, New York, NY.
Greiner, R., 1985,Learning by Understanding Analogies, Ph.D. Dissertation, Computer Science Department, Stanford University, Stanford, Calif.
Hesse M.B., 1974,The Structure of Scientific Inferences, Univ. of California Press, Berkeley, Calif.
Hofstadter D.R. 1981/85. “Metamagical Themas: Roles and Analogies in Human and Machine Thought,”Scientific American, Vol. 245, No. 3, Sept. 1981; reprinted with some additional material as “Analogies and Role in Human and Machine Thinking”, inMetamagical Themas: Questing for the Essence of Mind and Pattern, Basic Books, Inc. (1985), New York; Chap. 24 (pp. 547–603).
Indurkhya B., 1989, “Modes of Analogy,” in K. P. Jantke (ed.)Analogical and Inductive Inference, Lecture Notes in Artificial Intelligence 397, Springer-Verlag (1989), Berlin, GDR, pp. 217–230.
Indurkhya B., 1990, “Metaphor as Change of Representation,” submitted toCognitive Science.
Indurkhya B., forthcoming,Metaphor and Cognition.
Keynes J.M., 1921,A Treatise on Probability, MacMillan & Co., London.
Koestler A., 1964,The Act of Creation, Hutchinsons of London; 2nd Danube ed., 1976.
Mal’cev A.I., 1973,Algebraic Systems, translated by B.D. Seckler and A.P. Doohovskoy, Springer-Verlag, Berlin, FRG.
Michalski R.S., 1986, “Understanding the Nature of Learning: Issues and Research Directions,” in R.S. Michalskiet al. (eds.),Machine Learning: An Artificial Intelligence Approach, Vol. 2, M. Kaufmann (1986), Los Altos, Calif., pp. 3–25.
Nii H.P., 1986, “Blackboard Systems,” Technical Report No. STAN-CS-86-1123 (also numbered KSL-86-18), Dept. of Computer Science, Stanford University, Stanford, Calif.
nO’Hara S., forthcoming, “An Algebraic Approach to Proportional Analogy,” Technical Report, Computer Science Department, Boston University, Boston, Mass.
Rosch E., 1978, “Principles of Categorization,” in E. Rosch and B.B. Lloyd (eds.)Cognition and Categorization, Lawrence Erlbaum Associates, Hillsdale, NJ, pp. 27–48.
Russell S.J., 1987,Analogical and Inductive Reasoning, Ph.D. Thesis, Computer Science Dept., Stanford University, Palo Alto, Calif.
Schön D.A., 1979, “Generative Metaphor: A Perspective on Problem-Setting in Social Policy,” in A. Ortony (ed.)Metaphor and Thought, Cambridge Univ. Press (1979), Cambridge, UK, pp. 154–283.
Wittgenstein L., 1953,Philosophical Investigations, 3rd ed., translated by G.E.M. Anscombe, Macmillan Publishing Company, Inc., New York, NY.
Author information
Authors and Affiliations
About this article
Cite this article
Indurkhya, B. On the role of interpretive analogy in learning. NGCO 8, 385–402 (1991). https://doi.org/10.1007/BF03037095
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF03037095