Abstract
Different formal learning models address different aspects of human learning. Below we compare Gold-style learning—interpreting learning as a limiting process in which the learner may change its mind arbitrarily often before converging to a correct hypothesis—to learning via queries—interpreting learning as a one-shot process in which the learner is required to identify the target concept with just one hypothesis. Although these two approaches seem rather unrelated at first glance, we provide characterizations of different models of Gold-style learning (learning in the limit, conservative inference, and behaviourally correct learning) in terms of query learning. Thus we describe the circumstances which are necessary to replace limit learners by equally powerful one-shot learners. Our results are valid in the general context of learning indexable classes of recursive languages.
In order to achieve the learning capability of Gold-style learners, the crucial parameters of the query learning model are the type of queries (membership, restricted superset, or restricted disjointness queries) and the underlying hypothesis space (uniformly recursive, uniformly r. e., or uniformly 2-r. e. families). The characterizations of Gold-style language learning are formulated in dependence of these parameters.
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.: Inductive inference of formal languages from positive data. Inform. Control 45, 117–135 (1980)
Angluin, D.: Queries and concept learning. Machine Learning 2, 319–342 (1988)
Angluin, D.: Queries revisited. Theoret. Comput. Sci. 313, 175–194 (2004)
Baliga, G., Case, J., Jain, S.: The synthesis of language learners. Inform. Comput. 152, 16–43 (1999)
Blum, M.: A machine-independent theory of the complexity of recursive functions. J. ACM 14, 322–336 (1967)
Blum, L., Blum, M.: Toward a mathematical theory of inductive inference. Inform. Control 28, 125–155 (1975)
Case, J., Lynes, C.: In: Proc. ICALP 1982, LNCS 140, pp. 107–115. Springer, Heidelberg (1982)
Gold, E.M.: Language identification in the limit. Inform. Control 10, 447–474 (1967)
Hopcroft, J.E., Ullman, J.D.: Introduction to Automata Theory, Languages, and Computation. Addison-Wesley Publishing Company, Reading (1979)
Lange, S., Zeugmann, T.: Language learning in dependence on the space of hypotheses. In: Proc. COLT 1993, pp. 127–136. ACM Press, New York (1993)
Lange, S., Zilles, S.: On the learnability of erasing pattern languages in the query model. In: Gavaldá, R., Jantke, K.P., Takimoto, E. (eds.) ALT 2003. LNCS (LNAI), vol. 2842, pp. 129–143. Springer, Heidelberg (2003)
Rogers Jr, H.: Theory of Recursive Functions and Effective Computability. MIT Press, Cambridge (1987)
Stephan, F.: Degrees of Computing and Learning. Habilitationsschrift, Ruprecht- Karls-Universität, Heidelberg (1999)
Zeugmann, T., Lange, S.: A guided tour across the boundaries of learning recursive languages. In: Algorithmic Learning for Knowledge-Based Systems. LNCS (LNAI), vol. 961, pp. 190–258. Springer, Heidelberg (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lange, S., Zilles, S. (2004). Replacing Limit Learners with Equally Powerful One-Shot Query Learners. In: Shawe-Taylor, J., Singer, Y. (eds) Learning Theory. COLT 2004. Lecture Notes in Computer Science(), vol 3120. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27819-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-27819-1_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22282-8
Online ISBN: 978-3-540-27819-1
eBook Packages: Springer Book Archive