Abstract
A wide class of regular expressions non-representable as unions of “smaller” expressions is shown to be polynomial-time learnable via restricted subset queries from arbitrary representative examples “reflecting” the loop structure and a way the input example is obtained from the unknown expression. The corresponding subclass of regular expressions of loop depth at most 1 is shown to be learnable from representative examples via membership queries. A wide class of expressions with loops A + of arbitrary loop depth is shown to be learnable via restricted subset queries from arbitrary examples.
Preview
Unable to display preview. Download preview PDF.
References
J.M.Barzdin. Some rules of inductive inference and their use for program synthesis. In: Information Proc'83, North-Holland, 1983, 333–338.
A.N. Brazma. Inductive synthesis of dot expressions. Lecture Notes in Comp. Sci., v.502, 1991, 156–212.
E.B. Kinber. Some models of inductive syntactical synthesis from sample computations. Lecture Notes in Comp. Sci., v.502, 1991, 213–252.
L.Pitt. Inductive inference, DFAs, and computational complexity. Proc. of International Workshop AII'89, Lecture Notes in Comp. Sci., v.397, 1989, 18–44.
L.Pitt, M.K.Warmuth. The minimum consistent DFA problem cannot be approximated within any polynomial. Report NO. UIUCDC-R-89-1499, Urbana, Illinois, 1989.
D.Angluin. Queries and concept learning. Machine learning, 2, 1987, 319–342.
D.Angluin. Learning regular sets from queries and counterexamples. Information and Computation, v.75, 2, 1987, 87–106.
D.Angluin. A note on the number of queries needed to identify regular languages. Information and Computation, v.51, 1981, 76–87.
Y.Sakakibara. Learning context-free grammars from structural data in polynomial time. Proc. of the 1988 Workshop on Comp. Learn.Theory, D.Haussler, L.Pitt eds., Morgan Kaufmann, San Mateo, 1988, 330–344.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kinber, E. (1992). Learning a class of regular expressions via restricted subset queries. In: Jantke, K.P. (eds) Analogical and Inductive Inference. AII 1992. Lecture Notes in Computer Science, vol 642. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56004-1_16
Download citation
DOI: https://doi.org/10.1007/3-540-56004-1_16
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56004-3
Online ISBN: 978-3-540-47339-8
eBook Packages: Springer Book Archive