Abstract
We investigate the problem of case-based learning of formal languages. Case-based reasoning and learning is a currently booming area of artificial intelligence. The formal framework for case-based learning of languages has recently been developed by [JL93] in an inductive inference manner.
In this paper, we first show that any indexed class of recursive languages in which finiteness is decidable is case-based representable, but many classes of languages including the class of all regular languages are not case-based learnable with a fixed universal similarity measure, even if both positive and negative examples are presented.
Next we consider a framework of case-based learning where the learning algorithm is allowed to learn similarity measures, too. To avoid trivial encoding tricks, we carefully examine to what extent the similarity measure is going to be learned. Then by allowing only to learn a few parameters in the similarity measures, we show that any indexed class of recursive languages whose finiteness problem is decidable is case-based learnable. This implies that all context-free languages are case-based learnable by collecting cases and learning parameters of the similarity measures.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
David W. Aha, Dennis Kibler, and Marc K. Albert. Instance-based learning algorithms. Machine Learning, 6:37–66, 1991.
Dana Angluin. Inductive inference of formal languages from positive data. ACM Computing Surveys, 15:237–269, 1983.
Dana Angluin and Carl H. Smith. Inductive inference: Theory and methods. Information and Control, 45:117–135.
Scott Cost and Steven Salzberg. A weighted nearest neighbor algorithm for learning with symbolic features. Machine Learning, 10:57–78, 1993.
E. Mark Gold. Language identification in the limit. Information and Control, 10:447–474, 1967.
John E. Hopcroft and Jeffrey D. Ullman. Introduction to Automata Theory, Languages, and Computation. Addison-Wesley, 1979.
Klaus P. Jantke. Case-based learning in inductive inference. In Proceedings of 5th Workshop on Computational Learning Theory (COLT'92), pages 218–223. ACM Press, 1992.
Klaus P. Jantke. Types of incremental learning. In Working Notes, AAAI Spring Symposium on Training Issues in Incremental Learning, pages 26–32, Stanford University, 1993.
Klaus P. Jantke and Steffen Lange. Case-based representation and learning of pattern languages. In Proceedings of 4th Workshop on Algorithmic Learning Theory (ALT'93), Lecture Notes in Artificial Intelligence 744, pages 87–100. Springer-Verlag, 1993.
Ronald L. Rivest. Learning decision lists. Machine Learning, 2:229–246, 1987.
Yasubumi Sakakibara and Rani Siromoney. A noise model on learning sets of strings. In Proceedings of 5th Workshop on Computational Learning Theory (COLT'92), pages 295–302. ACM Press, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sakakibara, Y., Jantke, K.P., Lange, S. (1994). Learning languages by collecting cases and tuning parameters. 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_88
Download citation
DOI: https://doi.org/10.1007/3-540-58520-6_88
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