Abstract
This paper treats the inductive inference of computable functions the observations of which are falsified by noise. The effect of noise is assumed to satisfy a recursion theoretic randomness condition. It turns out that under three natural assumptions (finite range, reliable identifiability of the function class and "proper" noise function) the identifiability is preserved up to a finite set of anomalies.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Klette, R. / Wiehagen, R., Research in the theory of inductive inference by GDR mathematicians — a survey. Information Sciences 22(1980) 149–169
Grabowski,J. Ein Fortsetzungsprinzip in der Erkennungstheorie und seine Anwendung. In: Strukturerkennung diskreter kybernetischer Systems (ed. R.Lindner, H.Thiele). Seminarberichte der Sektion Mathematik Nr. 82. Humboldt-Universität zu Berlin 1986
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1987 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Grabowski, J. (1987). Inductive inference of functions from noised observations. In: Jantke, K.P. (eds) Analogical and Inductive Inference. AII 1986. Lecture Notes in Computer Science, vol 265. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-18081-8_85
Download citation
DOI: https://doi.org/10.1007/3-540-18081-8_85
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-18081-4
Online ISBN: 978-3-540-47739-6
eBook Packages: Springer Book Archive