Abstract
The present work investigates to which extent semantical knowledge can support the learning of basic mathematical concepts. The considered learning criteria are learning characteristic or enumerable indices for languages from positive data where the learner has to converge either syntactically (Ex) or semantically (BC). The considered classes are the classes of all monoids of a given group, all ideals of a given ring or all subspaces of a given vector space. The following is shown:
-
(a)
Learnability depends much on the amount of semantic knowledge given at the synthesis of the learner where this knowledge is represented by programs for the algebraic operations, codes for prominent elements of the algebraic structure (like 0 and 1 in fields) and certain parameters (like the dimension of finite dimensional vector spaces). For several natural examples good knowledge of the semantics may enable to keep ordinal mind change bounds while restricted knowledge may either allow only BC-convergence or even not permit learnability at all.
-
(b)
A recursive commutative ring is Noetherian iff the class of its ideals is BC-learnable. Such a BC-learner can be synthesized from programs for addition and multiplication. In many Noetherian rings, one can Ex-learn characteristic indices for the ideals with an ordinal bound on the number of mind changes. But there are also some Noetherian rings where it is impossible to Ex-learn the ideals or to learn characteristic indices for them.
A more comprehensive version of this paper is available as Forschungsbericht Mathematische Logik 34 of the Mathematisches Insitut at the UniversitÄt Heidelberg (same authors and title). This paper was written when Frank Stephan was visiting Arun Sharma at the School of Computer Science and Engineering, UNSW. The first author is supported by the Deutsche Forschungsgemeinschaft (DFG) grant Am 60/9-2. The second author is supported by the Australian Research Council grant A49600456 to Arun Sharma. The latter grant also supported the first author’s visit to UNSW.
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
Leonard Adleman and Manuel Blum: Inductive Inference and Unsolvability. Journal of Symbolic Logic, 56:891–900, 1991.
Andris Ambainis, Sanjay Jain and Arun Sharma: Ordinal mind change complexity of language identification. Submitted for publication.
Dana Angluin: Inductive Inference of Formal Languages from Positive Data. Information and Control, 45:117–135, 1980.
Ganesh Baliga and John Case: Learning with Higher Order Additional Information. Proceedings of the Fifth International Workshop on Algorithmic Learning Theory, Reinhardsbrunn, 64–75, 1994.
Walter Baur: Rekursive Algebren mit Kettenbedingungen. Zeitschrift für mathematische Logik und Grundlagen der Mathematik, 20:37–46, 1974.
Lenore Blum and Manuel Blum: Toward a mathematical theory of inductive inference. Information and Control, 28:125–155, 1975.
Leonore Blum, Micheal Shub and Steve Smale: On a theory of computation and complexity over the real numbers: NP-completeness, recursive functions and universal machines. Bulletin of the American Mathematical Society, 21:1–46, 1989.
Henri Cohen: A Course in Computational Algebraic Number Theory. Springer, Heidelberg, 1993.
David Eisenbud: Commutative Algebra with a View Toward Algebraic Geometry. Springer, Heidelberg, 1995.
RŪsiņš Freivalds and Carl H. Smith: On the Role of Procrastination for Machine Learning. Information and Computation, 107:237–271, 1993.
Mark A. Fulk: Saving the Phenomena: Requirements that Inductive Inference Machines Not Contradict Known Data. Information and Computation, 79:193–209, 1988.
E. Mark Gold: Language Identification in the Limit. Information and Control, 10:447–474, 1967.
Grete Hermann: Die Frage der endlich vielen Schritte in der Theorie der Polynomideale. Mathematische Annalen, 95:736–788, 1926.
Klaus Peter Jantke: Automatic synthesis of programs and inductive inference of functions. Proceedings of the International Conference on Fundamentals of Computations Theory, 219–225, 1979.
Irving Kaplansky: Commutative Rings. Allyn and Bacon, Inc., Boston, 1970.
Shyam Kapur and Gianfranco Bilardi: On uniform learnability of language families. Information Processing Letters, 44:35–38, 1992.
N. Kh. Kasymov: Logical programming without equality and constructive representations. Vychisl. Sist. 122:3–18, 1987.
Susanne Kaufmann and Frank Stephan: Robust Learning with Infinite Additional Information. Proceedings of the Third European Conference on Computational Learning Theory-EuroCOLT’97, Springer LNCS 1208, 316–330, 1997.
Satoshi Kobayashi and Takashi Yokomori: On approximately identifying concept classes in the limit. Proceedings of the Sixth International Workshop on Algorithmic Learning Theory-ALT’95, Springer LNCS 997, 298–312, 1995.
Satoshi Kobayashi: Approximate identification, finite elasticity and lattice structure of hypothesis space. Technical Report CSIM 96-04, Department of Computer Science and Information Mathematics, University of Electro-Communications, 1996.
Satoshi Kobayashi and Takashi Yokomori: Identifiability of subspaces and homomorphic images of zero-reversible languages. Proceedings of the Eighth International Workshop on Algorithmic Learning Theory-ALT’97, Springer LNCS 1316, 48–61, 1997.
Emmy Noether: Idealtheorie in Ringbereichen. Mathematische Annalen, 83:24–66, 1921.
Piergiorgio Odifreddi: Classical recursion theory. North-Holland, Amsterdam, 1989.
Daniel N. Osherson, Michael Stob and Scott Weinstein: Systems that learn. Bradford / MIT Press, London, 1986.
Daniel N. Osherson, Michael Stob and Scott Weinstein: Synthesizing inductive expertise. Information and Computation, 77:138–161, 1988.
Robert Soare: Recursively enumerable sets and degrees. Springer-Verlag, Heidelberg, 1987.
Frank Stephan and Sebastiaan Terwijn: The complexity of universal text-learners. Proceedings of the Eleventh International Symposium on Fundamentals of Computation Theory-FCT’ 97, Springer LNCS 1279, 441–451, 1997.
Thomas Zeugmann and Steffen Lange: A Guided Tour Across the Boundaries of Learning Recursive Languages. Algorithmic Learning for Knowledge-Based Systems, Springer LNCS 961, 193–262, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stephan, F., Ventsov, Y. (1998). Learning Algebraic Structures from Text Using Semantical Knowledge. In: Richter, M.M., Smith, C.H., Wiehagen, R., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 1998. Lecture Notes in Computer Science(), vol 1501. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49730-7_24
Download citation
DOI: https://doi.org/10.1007/3-540-49730-7_24
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65013-3
Online ISBN: 978-3-540-49730-1
eBook Packages: Springer Book Archive