Abstract
In this work, approximate inference of random partial Subsequential Transducers (STs) is addressed. Accessibility and distinguishability of a ST are defined and used to bound the maximum length of samples which are going to form representative sets for target STs. From these representative sets, the sample density required to obtain good approximate STs has been investigated. Dependency of the sample density on the number of states and on the accessibility and distinguishability of the target STs has been evaluated. As a general result, a decrease of the sample density has been found as these parameters increase, suggesting that accessibility and distinguishability are parameters as important as the number of states to evaluate learnability of STs.
Work partially supported by the Spanish CICYT, under grant TIC97-0745-C02-01.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
D. Angluin. “On the Complexity of Minimum Inference of Regular Sets”, Information and Control, Vol. 39, pp. 337–350. 1978.
J. Berstel. Transductions and Context-Free Languages. Teubner, Stuttgart. 1979.
A. Castellanos. “Funciones y Transductores Subsecuenciales”, Technical Report, UPI 01-03/98, Universitat Jaume I, Castellan, Spain. 1998. (In Spanish)
A. Castellanos. “Aprendizaje Aproximado de Transductores Subsecuenciales Aleatorios”, Technical Report, UPI 02-03/98, Universitat Jaume I, Castellón, Spain. 1998. (In Spanish)
E. M. Gold. “Complexity of Automaton Identification from Given Data”, Information and Control, Vol. 37, pp. 302–320. 1978.
C. de la Higuera. “Characteristic sets for polynomial grammatical inference”, in LNAI (1147): Grammatical Inference. Learning Syntax from Sentences, L. Miclet and C. de la Higuera (eds.), Springer-Verlag. Berlin, Germany, pp. 59–71. 1996.
K. J. Lang. “Random DFA's can be Approximately Learned from Sparse Uniform Examples”, in Proceedings of the 5th ACM Workshop on Computational Learning Theory, pp. 45–52. 1992.
J. Oncina, P. García. “Inductive Inference of Subsequential Functions”, Technical Report DSIC-II/34/91, Univ. Politécnica de Valencia, Spain. 1991.
J. Oncina, P. García. “Inferring Regular Languages in Polynomial Update Time”, in Series in Machine Perception and Artificial Intelligence (1): Pattern Recognition and Image Analysis, N. Pérez de la Blanca, A. Sanfeliu and E. Vidal (eds.), World Scientific, pp. 49–61. 1992.
J. Oncina, P. García, E. Vidal. “Learning Subsequential Transducers for Pattern Recognition Interpretation Tasks”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 15, pp. 448–458. 1993.
L. Pitt. “Inductive Inference, DFAs, and Computational Complexity”, in Lecture Notes in Artificial Intelligence (397): Analogical and Inductive Inference, K. P. Jantke (ed.), Springer-Verlag, pp. 18–44. 1989.
L. Pitt, M. K. Warmuth. “The Minimum Consistent DFA Problem Cannot be Approximated within any Polynomial”, Journal of the Association for Computing Machinery, Vol. 40, pp. 95–142. 1993.
B. A. Trakhtenbrot, Ya. M. Barzdin'. Finite Automata: Behavior and Synthesis. North Holland Publ. Co., Amsterdam. 1973.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Castellanos, A. (1998). Approximate learning of random subsequential transducers. In: Honavar, V., Slutzki, G. (eds) Grammatical Inference. ICGI 1998. Lecture Notes in Computer Science, vol 1433. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0054065
Download citation
DOI: https://doi.org/10.1007/BFb0054065
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64776-8
Online ISBN: 978-3-540-68707-8
eBook Packages: Springer Book Archive