Abstract
Bārzdiņš conjectured that only recursively enumerable classes of functions can be learned robustly. This conjecture, which was finally refuted by Fulk, initiated the study of notions of robust learning. The present work surveys research on robust learning and focuses on the recently introduced variants of uniformly robust and hyperrobust learning. Proofs are included for the (already known) results that uniformly robust Ex-learning is more restrictive than robust Ex-learning, that uniformly robustly Ex-learnable classes are consistently learnable, that hyperrobustly Ex-learnable classes are in Num and that some hyperrobustly BC-learnable class is not in Num.
Sanjay Jain is supported in part by the NUS grant number RP3992710.
Frank Stephan is supported by the Deutsche Forschungsgemeinschaft (DFG) Heisenberg grant Ste 967/1-1; part of the work was done while he visited the University of Wisconsin - Madison.
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
Janis Bārzdiņš. Inductive inference of automata, functions and programs. In Int. Math. Congress, Vancouver, pages 771–776, 1974.
Janis Bārzdiņš. Two theorems on the limiting synthesis of functions. In Theory of Algorithms and Programs, Latvian State University, Riga, 210:82–88, 1974.
Lenore Blum and Manuel Blum. Towards a mathematical theory of inductive inference. Information and Control, 28:125–155, 1975.
John Case. Learning Machines. In Demopoulos, W. and Marras, A., editors, Language Learning and Concept Acquisition, pages 83–102, Ablex Publishing Company, 1986.
John Case, Sanjay Jain, Matthias Ott, Arun Sharma and Frank Stephan. Robust learning aided by context. Journal of Computer and System Sciences (Special Issue COLT 1998), 60:234–257, 2000. Extended Abstract in Proceedings of the Eleventh Annual ACM Conference on Computational Learning Theory — COLT 1998, ACM-Press, 44–55, 1998.
John Case, Sanjay Jain, Frank Stephan and Rolf Wiehagen. Robust learning — rich and poor. Proceedings of the Fourteenth Annual Conference on Computational Learning Theory and the Fifth European Conference on Computational Learning Theory — COLT 2001 and EuroCOLT 2001, Springer LNAI 2111:143–159, 2001. Also available as: Technical Report LSA-2000-03E, Centre for Learning Systems and Applications, Department of Computer Science, University of Kaiserslautern, 2000.
John Case, Susanne Kaufmann, Efim Kinber and Martin Kummer. Learning recursive functions from approximations. Journal of Computer and System Sciences, 55:183–196, 1997.
John Case and Carl Smith. Comparison of identification criteria for machine inductive inference. Theoretical Computer Science, 25:193–220, 1983.
Jerome Feldmann. Some decidability results on grammatical inference and complexity. Information and Control, 20:244–262, 1972.
Mark Fulk. Robust separations in inductive inference. In Proceedings of the 31st Annual Symposium on Foundations of Computer Science (FOCS), pages 405–410, St. Louis, Missouri, 1990.
E. Mark Gold. Language identification in the limit. Information and Control, 10:447–474, 1967.
Sanjay Jain. Robust Behaviourally Correct Learning. Information and Computation, 153:238–248, 1999.
Sanjay Jain, Daniel Osherson, James Royer and Arun Sharma: Systems that Learn, Second Edition [of 19]. The MIT Press, Cambridge, Massachusetts, 1999.
Sanjay Jain, Carl Smith and Rolf Wiehagen. Robust Learning is Rich. Journal of Computer and System Sciences, 62:178–212, 2001.
Klaus-Peter Jantke and Hans-Rainer Beick. Combining postulates of naturalness in inductive inference. Journal of Information Processing and Cybernetics (EIK), 17:465–484, 1981.
Wolfgang Merkle and Frank Stephan. Trees and learning. In Proceedings of the Ninth Annual Conference on Computational Learning Theory (COLT), pages 270–279, ACM Press, New York, 1996.
Eliana Minicozzi. Some natural properties of strong-identification in inductive inference. Theoretical Computer Science, 2:345–360, 1976.
Piergiorgio Odifreddi. Classical Recursion Theory I and II. North-Holland, Amsterdam, 1989 and 1999.
Daniel Osherson, Michael Stob and Scott Weinstein. Systems that Learn. MIT Press, Cambridge, Massachusetts, 1986.
Matthias Ott and Frank Stephan. Avoiding coding tricks by hyperrobust learning. Proceedings of the Fourth European Conference on Computational Learning Theory — EuroCOLT 1999. Springer LNCS 1572, 183-197, 1999.
Lenny Pitt. Probabilistic inductive inference. Journal of the Association of Computing Machinery, 36:383–433, 1989.
Lenny Pitt and Carl Smith. Probability and plurality for aggregations of learning machines. Information and Computation, 77:77–92, 1998.
Karlis Podnieks. Comparing various concepts of function prediction, Part 1. Theory of Algorithms and Programs, Latvian State University, Riga, 210:68–81, 1974.
Carl Smith. The power of pluralism for automatic program synthesis Journal of the Association of Computing Machinery, 29:1144–1165, 1982.
Frank Stephan and Thomas Zeugmann. On the uniform learnability of approximations to non-recursive functions. Proceedings of the Ninth Annual Workshop on Algorithmic Learning Theory - ALT 1999, Springer LNCS 1720, 276–290, 1999. Also available as Learning Classes of Approximations to Non-Recursive Functions. Department of Informatics, Report 166, Kyushu University, Fukuoka, 1999.
Hermann Weyl. Symmetry. Princeton University Press, 1952
Rolf Wiehagen. Identification of formal languages. In Mathematical Foundations of Computer Science, Proceedings, 6th Symposium, Tatranska Lomnica, volume 53 of LNCS, pages 571–579. Springer, 1977.
Rolf Wiehagen. Zur Theorie der Algorithmischen Erkennung. Dissertation B, Humboldt University of Berlin, 1978.
Rolf Wiehagen and Walter Liepe. Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen. Journal of Information Processing and Cybernetics (EIK), 12:421–438, 1976.
Thomas Zeugmann. On the nonboundability of total effective operators. Zeitschrift für mathematische Logik und Grundlagen der Mathematik 30:169–172, 1984.
Thomas Zeugmann. On Bārzdiņš Conjecture. In K. P. Jantke, editor, Proceedings of the International Workshop on Analogical and Inductive Inference (AIP′86), volume 265 of LNCS, pages 220–227. Springer, 1986.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer Science+Business Media New York
About this chapter
Cite this chapter
Jain, S., Stephan, F. (2003). A Tour of Robust Learning. In: Computability and Models. The University Series in Mathematics. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0755-0_9
Download citation
DOI: https://doi.org/10.1007/978-1-4615-0755-0_9
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5225-9
Online ISBN: 978-1-4615-0755-0
eBook Packages: Springer Book Archive