Abstract
The traditional model of learning in the limit is restricted so as to allow the learning machines only a fixed, finite amount of memory to store input and other data. A class of recursive functions is presented that cannot be learned deterministically by any such machine, but can be learned by a memory limited probabilistic leaning machine with probability 1.
Supported in part by NSF Grant CCR-9020079.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Ablaev, F. M. and Freivalds, R. Why sometimes probabilistic algorithms can be more effective. In Lecture Notes in Computer Science, 233, 1986
Addanki, S. Connectionism. In The Encyclopedia of Artificial Intelligence, S. Shapiro, Ed., John Wiley and Sons Inc., New York, NY, 1987
Angluin, D. and Smith, C. H. Inductive inference: theory and methods. Computing Surveys 15, 237–269 (1983)
Angluin, D. and Smith, C. H. Inductive inference. In Encyclopedia of Artificial Intelligence, S. Shapiro, Ed., John Wiley and Sons Inc., 1987
Blum, L. and Blum, M. Toward a mathematical theory of inductive inference. Information and Control 28, 125–155 (1975)
Case, J. and Ngomanguelle, S. Refinements of inductive inference by popperian machines. Kybernetika (19??) to appear.
Case, J. and Smith, C. Comparison of identification criteria for machine inductive inference. Theoretical Computer Science 25, 2, 193–220 (1983)
Feldman, J. A. and Ballard, D. H. Connectionist models and their properties. Cognitive Science 6, 3, 205–254 (1982)
Feller, W.An Introduction to Probability Theory and its Applications. Wiley, New York, 1968 Third Edition.
Freivalds, R. and Smith, C. On the power of procrastination for machine learning. Manuscript.
Fulk, M. and Case, J.Proceedings of the Third Annual Workshop on Computational Learning Theory. Margan Kaufmann Publishers, Palo Alto, CA., 1990
Gold, E. M. Language identification in the limit. Information and Control 10, 447–474 (1967)
Haussler, D. and Pitt, L.Proceedings of the 1988 Workshop on Computational Learning Theory. Margan Kaufmann Publishers, Palo Alto, CA., 1988
Heath, D., Kasif, S., Kosaraju, R., Salzberg, S., and Sullivan, G.Learning nested concept classes with limited storage. Computer Science Department, Johns Hopkins University, Baltimore MD., 1990
Kleene, S. On notation for ordinal numbers. Journal of Symbolic Logic 3, 150–155 (1938)
Machtey, M. and Young, P.An Introduction to the General Theory of Algorithms. North-Holland, New York, 1978
Michalski, R., Carbonell, J., and Mitchell, T.Machine Learning. Tioga Publishing Co., Palo Alto, CA, 1983
Miyahara, T. Inductive inference by iteratively working and consistent strategies with anomalies. Bulletin of Informatics and Cybernetics 22, 171–177 (1987)
Miyahara, T. A note on iteratively working strategies in inductive inference. In Proceedings of the Fujitsu IIAS-SIS Workshop on Computational Learning Theory, Numazu, Japan, 1989
Osherson, D., Stob, M., and Weinstein, S.Systems that Learn. MIT Press, Cambridge, Mass., 1986
Pitt, L. A Characterization of Probabilistic Inference. Journal of the ACM 36, 2, 383–433 (1989)
Pitt, L. and Smith, C. Probability and plurality for aggregations of learning machines. Information and Computation 77, 77–92 (1988)
Popper, K.The Logic of Scientific Discovery. Harper Torch Books, N.Y., 1968 2nd Edition.
Rivest, R., Haussler, D., and Warmuth, M.Proceedings of the Second Annual Workshop on Computational Learning Theory. Margan Kaufmann Publishers, Palo Alto, CA., 1989
Rogers, H. Jr. Gödel numberings of partial recursive functions. Journal of Symbolic Logic 23, 331–341 (1958)
Shapiro, S.Encyclopedia of Artificial Intelligence. John Wiley and Sons Inc., New York, NY, 1987
Taimina, D. Ya. and Freivalds, R. On complexity of probabilistic finite automata recognizing superlanguages. In Methods of logic in construction of effective algorithms, Kalinin State University, 1966 In Russian.
Warmuth, M. and Valiant, L.Proceedings of the 1991 Workshop on Computational Learning Theory. Margan Kaufmann Publishers, Palo Alto, CA., 1991
Wiehagen, R. Limes-erkennung rekursiver funktionen durch spezielle strategien. Elektronische Informationsverarbeitung und Kybernetik 12, 93–99 (1976)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Freivalds, R., Smith, C.H. (1992). Memory limited inductive inference machines. In: Nurmi, O., Ukkonen, E. (eds) Algorithm Theory — SWAT '92. SWAT 1992. Lecture Notes in Computer Science, vol 621. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-55706-7_2
Download citation
DOI: https://doi.org/10.1007/3-540-55706-7_2
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-55706-7
Online ISBN: 978-3-540-47275-9
eBook Packages: Springer Book Archive