Abstract
Usually “quality” of learning grows with experience. Here is given a formalization of that phenomenon within a recursion theoretic framework. We consider the learning of total recursive functions by some algorithmic device (inductive inference machine) and describe the “quality” of learning in two different ways: as probability with which machine identifies the given function correctly, and as density of a set of arguments for which the hypothesis given by machine coincides with the identifiable function. We prove that in both cases there exist classes of sets of total recursive functions, such that for each of these sets the “quality” with which a learning device can identify an arbitrary function from the set grows with the number of other functions, which learning device are trying to identify at the same time, i.e., these classes are identifiable only with learning devices that show some improvement of learning capabilities with practice.
Preview
Unable to display preview. Download preview PDF.
References
D.Angluin, W.Gasarch and C.Smith. Training sequences. Theoretical Computer Science 66 (1989), p.255–272.
D.Angluin and C.Smith. Inductive inference: theory and methods. ACM Computing Surveys 15 (1983), p.237–269.
L.Blum and M.Blum. Toward a mathematical theory of inductive inference. Information and Control 28 (1975), p.125–155.
J.Case and C.Smith. Comparison of identification criteria for machine inductive inference. Theoretical Computer Science 25 (1983), p. 193–220.
W.Gasarch and C.Smith. On the inference of sequences of functions. Lecture Notes in Computer Science 265 (1987), p.23–41.
L.Pitt. Probabilistic inductive inference. Journal of the ACM 36 (1989), p.383–433.
H.Rogers. Theory of Recursive Functions and Effective Computability. MIT Press, 1987.
J.Royer. Inductive inference of approximations. Information and Computation 70 (1986), p.156–178.
C.Smith. The power of pluralism for automatic program synthesis. Journal of the ACM 29 (1982), p.1144–1165.
C.Smith and M.Velauthapillai. On the inference of approximate programs. Theoretical Computer Science 77 (1990), p.249–266.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Viksna, J. (1993). Learning with growing quality. In: Jantke, K.P., Kobayashi, S., Tomita, E., Yokomori, T. (eds) Algorithmic Learning Theory. ALT 1993. Lecture Notes in Computer Science, vol 744. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57370-4_45
Download citation
DOI: https://doi.org/10.1007/3-540-57370-4_45
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57370-8
Online ISBN: 978-3-540-48096-9
eBook Packages: Springer Book Archive