Abstract
Given a set \(\mathcal{W}\) of logical structures, or possible worlds, a set \(\mathcal{D}\) of logical formulas, or possible data, and a logical formula ϕ, we consider the classification problem of determining in the limit and almost always correctly whether a possible world \(\mathcal{M}\) satisfies ϕ, from a complete enumeration of the possible data that are true in \(\mathcal{M}\). One interpretation of almost always correctly is that the classification might be wrong on a set of possible worlds of measure 0, w.r.t. some natural probability distribution over the set of possible worlds. Another interpretation is that the classifier is only required to classify a set \(\mathcal{W}'\) of possible worlds of measure 1, without having to produce any claim in the limit on the truth of ϕ in the members of the complement of \(\mathcal{W}'\) in \(\mathcal{W}\). We compare these notions with absolute classification of \(\mathcal{W}\) w.r.t. a formula that is almost always equivalent to ϕ in \(\mathcal{W}\), hence investigate whether the set of possible worlds on which the classification is correct is definable. Finally, in the spirit of the kind of computations considered in Logic programming, we address the issue of computing almost correctly in the limit witnesses to leading existentially quantified variables in existential formulas.
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
Ambainis, A.: Probabilistic Inductive Inference: a Survey. Theoretical Computer Science 264, 155–167 (2001)
Bārzdiņš, J., Freivalds, R., Smith, C.: Learning formulae from elementary facts. In: Ben-David, S. (ed.) EuroCOLT 1997. LNCS, vol. 1208, pp. 272–285. Springer, Heidelberg (1997)
Ben-David, S.: Can Finite Samples Detect Singularities of Read-Valued Functions? In: Proceedings of the 24th Annual ACM Symposium on the Theory of Computer Science, Victoria, B.C., pp. 390–399 (1992)
Büchi, J.: On a decision method in restricted second order arithmetic. In: Proc. of the International Congress on Logic, Methodology and Philosophy of Science, pp. 1–11. Stanford Univ. Press, Stanford (1960)
Caldon, P., Martin, É.: Limiting resolution: From foundations to implementation. In: Demoen, B., Lifschitz, V. (eds.) ICLP 2004. LNCS, vol. 3132, pp. 149–164. Springer, Heidelberg (2004)
Daley, R.: Inductive Inference Hierarchies: Probabilistic vs. Pluralistic. In: Bibel, W., Jantke, K.P. (eds.) Mathematical Methods of Specification and Synthesis of Software Systems 1985. LNCS, vol. 215, pp. 73–82. Springer, Heidelberg (1985)
Freivalds, R.: Finite Identification of General Recursive Functions by Probabilistic Strategies. In: Proceedings of the Conference on Fundamentals of Computation Theory, pp. 138–145. Akademie Verlag, Berlin (1979)
Gasarch, W., Pleszkoch, M., Stephan, F., Velauthapillai, M.: Classification Using Information. Annals of Math. and Artificial Intelligence 23, 147–168 (1998)
Martin, É., Sharma, A., Stephan, F.: Learning, logic, and topology in a common framework. In: Cesa-Bianchi, N., Numao, M., Reischuk, R. (eds.) ALT 2002. LNCS (LNAI), vol. 2533, pp. 248–262. Springer, Heidelberg (2002)
Meyer, L.: Probabilistic language learning under monotonicity constraints. Theoretical Computer Science 185, 81–128 (1997)
Pitt, L.: Probabilistic Inductive Inference. Journal of the Association for Computing Machinery 36, 333–383 (1989)
Pitt, L., Smith, C.: Probability and plurality for aggregations of learning machines. Information and Computation 77, 77–92 (1988)
Rogers Jr., H.: Theory of recursive functions and effective computability. McGraw-Hill Book Company, New York (1967)
Smith, C.: The power of pluralism for automatic program synthesis. Journal of the Association for Computing Machinery 29, 1144–1165 (1982)
Takeuti, I.: The measure of an omega regular language is rational, Available at http://www.sato.kuis.kyoto-u.ac.jp/~takeuti/art/regular.ps
Voronkov, A.: Logic programming with bounded quantifiers. In: Proc. LPAR. LNCS, vol. 592, pp. 486–514. Springer, Heidelberg (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jain, S., Martin, E., Stephan, F. (2005). Absolute Versus Probabilistic Classification in a Logical Setting. In: Jain, S., Simon, H.U., Tomita, E. (eds) Algorithmic Learning Theory. ALT 2005. Lecture Notes in Computer Science(), vol 3734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11564089_26
Download citation
DOI: https://doi.org/10.1007/11564089_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29242-5
Online ISBN: 978-3-540-31696-1
eBook Packages: Computer ScienceComputer Science (R0)