Abstract
We define a logic for machine discovery, which we call learning with justified refutation, in the style of Mukouchi and Arikawa's learning with refutation. By comparison, our model is more tolerant of the learning agent's behaviour in two particular cases, which we call the cases of incomplete and ambiguous data, respectively. Consequently our formalism correctly learns or refutes a wider spectrum of language classes than its forerunner.
We compare the class of language classes learnable with justified refutation with those learnable under other identification criteria. Comparison of learning with justified refutation from text and from informant shows that these two identification types are mutually incomparable in strength.
Finally we consider whether either of the two formalisms for machine discovery are truly in the tradition of Popper's logic of scientific discovery, the original inspiration for Mukouchi and Arikawa's work.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Work supported by the German Ministry for Research and Technology (BMFT) under contract no. 413-4001-01 IW 101 A
Preview
Unable to display preview. Download preview PDF.
References
Angluin, D. (1980), Inductive inference of formal languages from positive data, Information and Control 45, pp. 117–135.
Angluin, D. and Smith, C.H. (1983), Inductive inference: theory and methods, Computing Surveys 15, pp. 237–269.
Case, J. and Smith, C.H. (1983), Comparison of identification criteria for machine inductive inference, Theoretical Computer Science 25, pp. 193–220.
Daley, R., Kalyanasundaram, B. and Velauthapillai, M. (1994), The power of probabilism in Popperian FINite learning, Journal of Experimental and Theoretical Artificial Intelligence 6(1), pp. 41–62.
Gasarch, W.I. and Velauthapillai, M. (1992), Asking questions versus verifiability, in “Proceedings 3rd Intern. Workshop on Analogical and Inductive Inference,” Lecture Notes in Artificial Intelligence Vol. 642, Springer-Verlag, pp. 197–213.
Gold, E.M. (1967), Language identification in the limit, Information and Control 10, pp. 447–474.
Lange, S. and Zeugmann, T. (1992), Types of monotonic language learning and their characterization, in “Proceedings 5th Annual ACM Workshop on Computational Learning Theory,” ACM Press, pp. 377–390.
Lange, S. and Zeugmann, T. (1993), Learning recursive languages with bounded mind changes, International Journal of Foundations of Computer Science 4, pp. 157–178.
Machtey, M. and Young, P. (1978) “An Introduction to the General Theory of Algorithms,” North-Holland, Amsterdam.
Mukouchi, Y. (1994), Inductive inference of Recursive Concepts, Ph.D. Thesis, Technical Report RIFIS-TR-CS-82, Research Institute of Fundamental Information Science, Kyushu University, 1994.
Mukouchi, Y. and Arikawa, S. (1993), Inductive inference machines that can refute hypothesis spaces, in “Proceedings 4th Intern. Workshop on Algorithmic Learning Theory,” Lecture Notes in Artificial Intelligence Vol. 744, Springer-Verlag, pp. 123–136.
Osherson, D., Stob, M. and Weinstein, S. (1986), “Systems that Learn, An Introduction to Learning Theory for Cognitive and Computer Scientists,” MIT Press, Cambridge, Massachusetts.
Popper, K.R. (1965) “The Logic of Scientific Discovery,” Harper & Row, 1965.
Rogers, H. Jr. (1967) “Theory of Recursive Functions and Effective Computability,” McGraw-Hill, 1967.
Sakurai, A. (1991), Inductive inference of formal languages from positive data enumerated primitive-recursively, in “Proceedings 2nd Intern. Workshop on Algorithmic Learning Theory,” Ohmsha Ltd., pp. 73–83.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lange, S., Watson, P. (1994). Machine discovery in the presence of incomplete or ambiguous data. In: Arikawa, S., Jantke, K.P. (eds) Algorithmic Learning Theory. AII ALT 1994 1994. Lecture Notes in Computer Science, vol 872. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58520-6_82
Download citation
DOI: https://doi.org/10.1007/3-540-58520-6_82
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58520-6
Online ISBN: 978-3-540-49030-2
eBook Packages: Springer Book Archive