Abstract
This work extends studies of Angluin, Lange and Zeugmann on the dependence of learning on the hypotheses space chosen for the class. In subsequent investigations, uniformly recursively enumerable hypotheses spaces have been considered. In the present work, the following four types of learning are distinguished: class-comprising (where the learner can choose a uniformly recursively enumerable superclass as hypotheses space), class-preserving (where the learner has to choose a uniformly recursively enumerable hypotheses space of the same class), prescribed (where there must be a learner for every uniformly recursively enumerable hypotheses space of the same class) and uniform (like prescribed, but the learner has to be synthesized effectively from an index of the hypothesis space). While for explanatory learning, these four types of learnability coincide, some or all are different for other learning criteria. For example, for conservative learning, all four types are different. Several results are obtained for vacillatory and behaviourally correct learning; three of the four types can be separated, however the relation between prescribed and uniform learning remains open. It is also shown that every (not necessarily uniformly recursively enumerable) behaviourally correct learnable class has a prudent learner, that is, a learner using a hypotheses space such that it learns every set in the hypotheses space. Moreover the prudent learner can be effectively built from any learner for the class.
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. Information and Control 45, 117–135 (1980)
Baliga, G., Case, J., Merkle, W., Stephan, F., Wiehagen, R.: When unlearning helps. Technical Report TRA5/06, School of Computing, National University of Singapore (2005), Welzl, E., Montanari, U., Rolim, J.D.P. (eds.) ICALP 2000. LNCS, vol. 1853, pp. 844–855. Springer, Heidelberg (2000)
Bārzdiņš, J.: Two theorems on the limiting synthesis of functions. In: Theory of Algorithms and Programs– Volume 1, vol. 210, pp. 82–88. Latvian State University, Riga (1974)
Blum, L., Blum, M.: Toward a mathematical theory of inductive inference. Information and Control 28, 125–155 (1975)
Case, J.: The power of vacillation in language learning. SIAM Journal on Computing 28, 1941–1969 (1999)
Case, J., Lynes, C.: Inductive inference and language identification. In: Nielsen, M., Schmidt, E.M. (eds.) Ninth International Colloquium on Automata, Languages and Programming (ICALP). LNCS, vol. 140, pp. 107–115. Springer, Heidelberg (1982)
de Jongh, D., Kanazawa, M.: Angluin’s theorem for indexed families of r.e. sets and applications. In: Proceedings of the Ninth Annual Conference on Computational Learning Theory, pp. 193–204. ACM Press, New York (1996)
Friedberg, R.: Three theorems on recursive enumeration. Journal of Symbolic Logic 23, 309–316 (1958)
Fulk, M.: Prudence and other conditions on formal language learning. Information and Computation 85, 1–11 (1990)
Gold, E.M.: Language identification in the limit. Information and Control 10, 447–474 (1967)
Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems That Learn: An Introduction to Learning Theory. MIT-Press, Boston (1999)
Jain, S., Sharma, A.: Prudence in vacillatory language identification. Mathematical Systems Theory 28, 267–279 (1995)
Jain, S., Stephan, F.: Learning in Friedberg Numberings. In: Hutter, M., Servedio, R., Takimoto, E. (eds.) Algorithmic Learning Theory: 18th International Conference, ALT 2007, Sendai, Japan (to appear, 2007)
Kurtz, S., Royer, J.S.: Prudence in language learning. In: Proceedings of the First Annual Workshop on Computational Learning Theory, pp. 143–156. MIT, Cambridge (1988)
Lange, S., Zeugmann, T.: Language learning in dependence on the space of hypotheses. In: Proceedings of the Sixth Annual Conference on Computational Learning Theory, Santa Cruz, California, United States, pp. 127–136 (1993)
Lange, S., Zeugmann, T., Kapur, S.: Monotonic and dual monotonic language learning. Theoretical Computer Science 155, 365–410 (1996)
Li, M., Vitányi, P.: An Introduction to Kolmogorov Complexity and Its Applications. Springer, Heidelberg (1993)
Odifreddi, P.: Classical Recursion Theory, North-Holland, Amsterdam (1989)
Osherson, D., Stob, M., Weinstein, S.: Systems That Learn, An Introduction to Learning Theory for Cognitive and Computer Scientists. Bradford — The MIT Press, Cambridge, Massachusetts (1986)
Post, E.: Recursively enumerable sets of positive integers and their decision problems. Bulletin of the American Mathematical Society 50, 284–316 (1944)
Soare, R.: Recursively Enumerable Sets and Degrees. Springer, Heidelberg (1987)
Wiehagen, R.: A thesis in inductive inference. In: Dix, J., Schmitt, P.H., Jantke, K.P. (eds.) Proceedings First International Workshop on Nonmonotonic and Inductive Logic. LNCS, vol. 543, pp. 184–207. Springer, Heidelberg (1990)
Zeugmann, T.: Algorithmisches Lernen von Funktionen und Sprachen. Habilitationsschrift, Technische Hochschule Darmstadt (1993)
Zeugmann, T., Lange, S.: A guided tour across the boundaries of learning recursive languages. In: Lange, S., Jantke, K.P. (eds.) Algorithmic Learning for Knowledge-Based Systems. LNCS, vol. 961, pp. 193–262. Springer, Heidelberg (1995)
Zeugmann, T., Lange, S., Kapur, S.: Characterizations of monotonic and dual monotonic language learning. Information and Computation 120, 155–173 (1995)
Zilles, S.: Separation of uniform learning classes. Theoretical Computer Science 313, 229–265 (2004)
Zilles, S.: Increasing the power of uniform inductive learners. Journal of Computer and System Sciences 70, 510–538 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jain, S., Stephan, F., Ye, N. (2007). Prescribed Learning of R.E. Classes. In: Hutter, M., Servedio, R.A., Takimoto, E. (eds) Algorithmic Learning Theory. ALT 2007. Lecture Notes in Computer Science(), vol 4754. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75225-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-75225-7_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75224-0
Online ISBN: 978-3-540-75225-7
eBook Packages: Computer ScienceComputer Science (R0)