Abstract
Partial learning is a criterion where the learner infinitely often outputs one correct conjecture while every other hypothesis is issued only finitely often. This paper addresses two variants of partial learning in the setting of inductive inference of functions: first, confident partial learning requires that the learner also on those functions which it does not learn, singles out exactly one hypothesis which is output infinitely often; second, essentially class consistent partial learning is partial learning with the additional constraint that on the functions to be learnt, almost all hypotheses issued are consistent with all the data seen so far. The results of the present work are that confident partial learning is more general than explanatory learning, incomparable with behaviourally correct learning and closed under union; essentially class consistent partial learning is more general than behaviourally correct learning and incomparable with confident partial learning. Furthermore, it is investigated which oracles permit to learn all recursive functions under these criteria: for confident partial learning, some non-high oracles are omniscient; for essentially class consistent partial learning, all PA-complete and all oracles of hyperimmune Turing degree are omniscient.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bārzdiņš, J.: Two theorems on the limiting synthesis of functions. In: Theory of Algorithms and Programs, vol. 1, pp. 82–88. Latvian State University (1974) (in Russian)
Bārzdiņš, J.: Inductive inference of automata, functions and programs. In: Proceedings of the 20th International Congress of Mathematicians, Vancouver, pp. 455–560 (1974) (in Russian); English translation in American Mathematical Society Translations: Series 2 109, 107–112 (1977)
Blum, L., Blum, M.: Towards a mathematical theory of inductive inference. Information and Control 28, 125–155 (1975)
Feldman, J.: Some decidability results on grammatical inference and complexity. Information and Control 20, 244–262 (1972)
Gao, Z., Stephan, F., Wu, G., Yamamoto, A.: Learning Families of Closed Sets in Matroids. In: Dinneen, M.J., Khoussainov, B., Nies, A. (eds.) WTCS 2012 (Calude Festschrift). LNCS, vol. 7160, pp. 120–139. Springer, Heidelberg (2012)
Mark Gold, E.: Language identification in the limit. Information and Control 10, 447–474 (1967)
Grieser, G.: Reflective inductive inference of recursive functions. Theoretical Computer Science A 397(1-3), 57–69 (2008)
Hanf, W.: The Boolean algebra of logic. Bulletin of the American Mathematical Society 81, 587–589 (1975)
Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems that learn: an introduction to learning theory. MIT Press, Cambridge (1999)
Jain, S., Stephan, F.: Consistent partial identification. In: COLT 2009, pp. 135–145 (2009)
Jockusch Jr., C.G., Soare, R.I.: \(\prod^0_1\) classes and degrees of theories. Transactions of the American Mathematical Society 173, 33–56 (1972)
Lakatos, I.: The role of crucial experiments in science. Studies in History and Philosophy of Science 4(4), 319–320 (1974)
Kummer, M.: Numberings of \(\mathcal{R}_1\cup F\). In: Börger, E., Kleine Büning, H., Richter, M.M. (eds.) CSL 1988. LNCS, vol. 385, pp. 166–186. Springer, Heidelberg (1989)
Osherson, D.N., Stob, M., Weinstein, S.: Systems that learn: an introduction to learning theory for cognitive and computer scientists. MIT Press, Cambridge (1986)
Popper, K.R.: The logic of scientific discovery. Hutchinson, London (1959)
Rogers Jr., H.: Theory of recursive functions and effective computability. MIT Press, Cambridge (1987)
Wiehagen, R., Zeugmann, T.: Learning and Consistency. In: Lange, S., Jantke, K.P. (eds.) GOSLER 1994. LNCS (LNAI), vol. 961, pp. 1–24. Springer, Heidelberg (1995)
Zeugmann, T., Zilles, S.: Learning recursive functions: a survey. Theoretical Computer Science 397(1-3), 4–56 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gao, Z., Stephan, F. (2012). Confident and Consistent Partial Learning of Recursive Functions. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2012. Lecture Notes in Computer Science(), vol 7568. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34106-9_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-34106-9_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34105-2
Online ISBN: 978-3-642-34106-9
eBook Packages: Computer ScienceComputer Science (R0)