Abstract
Belief revision theory concerns methods for reformulating an agent's epistemic state when the agent's beliefs are refuted by new information. The usual guiding principle in the design of such methods is to preserve as much of the agent's epistemic state as possible when the state is revised. Learning theoretic research focuses, instead, on a learning method's reliability or ability to converge to true, informative beliefs over a wide range of possible environments. This paper bridges the two perspectives by assessing the reliability of several proposed belief revision operators. Stringent conceptions of “minimal change” are shown to occasion a limitation called inductive amnesia: they can predict the future only if they cannot remember the past. Avoidance of inductive amnesia can therefore function as a plausible and hitherto unrecognized constraint on the design of belief revision operators.
Similar content being viewed by others
REFERENCES
Arlo-Costa, H.: In press, ‘Belief Revision Conditionals: Basic Iterated Systems’, Annals of Pure and Applied Logic.
Boutilier, C.: 1993, ‘Revision Sequences and Nested Conditionals’, in Proceedings of the Third International Conference on Principles of Knowledge Representation and Reasoning, pp. 519-25.
Darwiche, A. and J. Pearl: 1997, ‘On the Logic of Iterated Belief Revision’, 89, 1-29.
Earman, J.: 1992, Bayes or Bust, MIT Press, Cambridge.
Gärdenfors, P.: 1988 Knowledge in Flux, MIT Press, Cambridge.
Glaister, S. M.: 1997, ‘Symmetry and Belief Revision’, unpublished manuscript.
Gold, E. M.: 1967 ‘Language Identification in the Limit’, Information and Control 10, 302-20.
Goldszmidt, M. and J. Pearl: 1994, ‘Qualitative Probabilities for Default Reasoning, Belief Revision, and Causal Modeling’, Technical Report r-161-L, Revision II.
Goodman, N.: 1983, Fact, Fiction and Forecast, 4th edn. Harvard University Press, Cambridge.
Grove, A.: 1988, ‘Two Modellings for Theory Change’, Journal of Philosohical Logic 17, 157-70.
James, W.: 1948, ‘The Will to Believe’, in A. Castell (ed), Essays in Pragmatism, Macmillan, New York.
Katsuno, H. and A. O. Mendelzon: 1991, ‘Propositional Knowledge Base Revision and Minimal Change’, Journal of Artificial Intelligence 52, 263-94.
Kelly, K. T.: 1996, The Logic of Reliable Inquiry, Oxford University Press, New York.
Kelly, K. T. and O. Schulte: 1995, ‘The Computable Testability of Theories Making Uncomputable Predictions’, Erkenntnis 43, 29-66.
Kelly, K. T., O. Schulte, and V. Hendricks: 1997, ‘Reliable Belief Revision’, in Maria Luisa Dalla Chiara (ed.), Proceedings of the 10th International Congress of Logic, Methodology, and Philosophy of Science, Kluwer, Dordrecht.
Kemeny, J.: 1953, ‘The Use of Simplicity in Induction’, Philosophical Review 62, 391-408.
Kuhn, T.: 1970, The Structure of Scientific Revolutions, University of Chicago Press, Chicago.
Levi, I.: 1996, The Enterprise of Knowledge, MIT Press, Cambridge.
Levi, I.: 1996, For the Sake of the Argument: Ramsey Test Conditionals, Inductive Inference, and Nonmonotonic Reasoning, Cambridge University Press, Cambridge.
Martin, E. and D. Osherson: 1997, ‘Scientific Discovery via Rational Hypothesis Revision’, in Maria Luisa Dalla Chiara (ed.), Proceedings of the 10th International Congress of Logic, Methodology, and Philosophy of Science, Kluwer, Dordrecht.
Martin, E. and D. Osherson: In press, ‘Scientific Discovery Based on Belief Revision’, Journal of Symbolic Logic.
Martin, E. and D. Osherson: 1998, Elements of Scientific Inquiry, MIT Press, Cambridge.
Nayak, A. C.: 1994, ‘Iterated Belief Change Based on Epistemic Entrenchment’, Erkenntnis 41, 353-90.
Oshersion, D., M. Stob, and S. Weinstein: 1986, Systems that Learn, MIT Press, Cambridge.
Popper, K.R.: 1968, The Logic of Scientific Discovery, Harper, New York.
Putnam, H.: 1963, ‘“Degree of Confirmation” and Inductive Logic’, in A. Schilpp (ed.), The Philosophy of Rudolph Carnap, Open Court, LaSalle, IL.
Ramsey, F.P.: 1990, in H. A. Mellor (ed.), Philosophical Papers, Cambridge University Press, Cambridge.
Samet, D.: 1996, ‘Hypothetical Knowledge and Games with Perfect Information’, Games and Economic Behavior 17, 230-51.
Spohn, W.: 1988, ‘Ordinal Conditional Functions: A Dynamic Theory of Epistemic States’, Causation in Decision, Belief Change, and Statistics, II, in B. Skyrms and W. L. Harper, (eds.), Kluwer, Dordrecht.
Spohn, W.: 1990, ‘A General Non-probabilisistic Theory of Inductive Reasoning’, Uncertainty in Artificial Intelligence 4, 149-59.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kelly, K.T. Iterated Belief Revision, Reliability, and Inductive Amnesia. Erkenntnis 50, 7–53 (1999). https://doi.org/10.1023/A:1005444112348
Issue Date:
DOI: https://doi.org/10.1023/A:1005444112348