Abstract
Case and Smith studied learning machines whose conjectures are verifiable (i.e. the conjectures are total programs). They discovered that such machines are weaker than machines whose conjectures are not verifiable. Gasarch and Smith studied learning machines that ask questions. They discovered that such machines are stronger than passive machines. We raise the question Can the weakness of verifiability be overcome by the strength of asking queries?
We answer many interesting questions along the way. These include a full examination of PEX and the resolution of some open problems of Gasarch Smith.
The motivating question has two answers: if unbounded mind changes are allowed then queries do not increase learning power of verifiable machines, where in the bounded case they do.
Supported by NSF grants CCR-880-3641 and CCR 9020079
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Angluin, D. and Smith, C. H. Inductive inference: theory and methods. Computing Surveys 15 (1983), 237–269.
Angluin, D. and Smith, C. H. Inductive inference. In Encyclopedia of Artificial Intelligence, S. Shapiro, Ed., John Wiley and Sons Inc., 1987.
Blum, L. and Blum, M. Toward a mathematical theory of inductive inference. Information and Control 28 (1975), 125–155.
Case, J. and Smith, C. Comparison of identification criteria for machine inductive inference. Theoretical Computer Science 25, 2 (1983), 193–220.
Daley, R. P. and Smith, C. H. On the complexity of inductive inference. Information and Control 69 (1986), 12–40.
Davis, M., H. Putnam, and Robinson, J. The decision problem for exponential diophantine equations. Annals of Mathematics 74 (1961), 425–436.
Davis, M. Hilbert's 10th problem is unsolvable. American Mathematical Monthly 80 (1973), 233–269.
Freivalds, R., Smith, C., and Velauthapillai, M. Trade-offs amongst parameters effecting the inductive inferribility of classes of recursive functions. Information and Computation 82, 3 (1989), 323–349.
Gasarch, W. and Smith, C. Learning via Queries. to appear in JACM.
Gasarch, W., Kinber, E., Pleszkoch, M., Smith, C., and Zeugmann, T. Learning via queries with teams and anomalies. Manuscript.
Gasarch, W., Pleszkoch, M., and Solovay, R. Learning via queries with plus and less than. to appear in JSL.
Gold, E. M. Language identification in the limit. Information and Control 10 (1967), 447–474.
Maciitey, M. and Young, P.An Introduction to the General Theory of Algorithms. North-Holland, New York, New York, 1978.
Matijasevic, Y. Enumerable sets are diophantine. Doklady Academy Nauk. SSSR 191 (1970), 279–282. Translation in Sov. Math. Dokl. 11, 1970, pp. 354–357.
Pleszkoch, M., Gasarch, W., Jain, S., and Solovay, R. Learning via queries to an oracle. Manuscript.
Rogers, H. Jr.Theory of Recursive Functions and Effective Computability. McGraw Hill, New York, 1967.
Smith, C. H. The power of pluralism for automatic program synthesis. Journal of the ACM 29, 4 (1982), 1144–1165.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1992 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gasarch, W.I., Velauthapillai, M. (1992). Asking questions versus verifiability. In: Jantke, K.P. (eds) Analogical and Inductive Inference. AII 1992. Lecture Notes in Computer Science, vol 642. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56004-1_14
Download citation
DOI: https://doi.org/10.1007/3-540-56004-1_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56004-3
Online ISBN: 978-3-540-47339-8
eBook Packages: Springer Book Archive