Abstract
We show that multiplicity automata (MAs) with size n and input alphabet ∑ can efficiently be learned from n(n+1)| ∑ |+2 smallest counterexamples. This improves on an earlier result of Bergadano and Varricchio. A unique representation for MAs is introduced. Our algorithm learns this representation. We also show that any learning algorithm for MAs needs at least \( \frac{1} {{64}}n^2 |\Sigma | \) smallest counterexamples. Thus our upper bound on the number of counterexamples cannot be improved substantially.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Angluin, D.: Learning Regular Sets from Queries and Counterexamples. Information and Computation 75 (1987) 87–106
Angluin, D.: Negative Results for Equivalence Queries. Machine Learning 5 (1990) 121–150
Beimel, A., Bergadano, F., Bshouty, N., Kushilevitz, E., Varricchio, S.: On the Applications of Multiplicity Automata in Learning. Proceedings of the 37th Annual Symposium on Foundations of Computer Science (1996) 349–358
Bergadano, F., Varricchio, S.: Learning Behaviors of Automata from Shortest Counterexamples. Proceedings of the 2nd European Conference on Computational Learning Theory (EUROCOLT 1995) 380–391
Birkendorf, A., Böker, A., Simon, H.U.: Learning Deterministic Finite Automata from Smallest Counterexamples. Proceedings of the 9th Annual ACM/SIAM Symposium on Discrete Algorithms (SODA 1998) 599–608
Carlyle, J.W., Paz, A.: Realization by Stochastic Finite Automata. Journal of Computer and System Sciences 5 (1971) 26–40
Fliess., M.: Matrices de Hankel. J. Math. Pures Appl. 53 (1974) 197–222. Erratum in vol. 54
Ibarra, O.H., Jiang, T.: Learning Regular Languages from Counterexamples. Journal of Computer and System Sciences 43 (1991) 299–316
Rivest, R.L., Shapire, R.E.: Inference on Finite Automata Using Homing Sequences. Information and Computation 103 (1993) 299–347
Vapnik, V.N., Chervonenkis, A.Y.: On the Uniform Convergence of Relative Frequencies of Events to their Probabilities. Theor. Probability and Appl. 16 (1971) 264–280
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Forster, J. (1999). Learning Multiplicity Automata from Smallest Counterexamples. In: Fischer, P., Simon, H.U. (eds) Computational Learning Theory. EuroCOLT 1999. Lecture Notes in Computer Science(), vol 1572. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49097-3_7
Download citation
DOI: https://doi.org/10.1007/3-540-49097-3_7
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65701-9
Online ISBN: 978-3-540-49097-5
eBook Packages: Springer Book Archive