Robust separations in inductive inference

Results in recursion-theoretic inductive inference have been criticized as depending on unrealistic self-referential examples. J.M. Barzdin (1974) proposed a way of ruling out such examples and conjectured that one of the earliest results of inductive inference theory would fall if his method were u...

Full description

Saved in:
Bibliographic Details
Published inFoundations of Computer Science, 31st Symposium pp. 405 - 410 vol.1
Main Author Fulk, M.A.
Format Conference Proceeding
LanguageEnglish
Published IEEE Comput. Soc. Press 1990
Subjects
Formal languages
Gold
Inference algorithms
Machine learning
Robustness
Online AccessGet full text
ISBN081862082X
9780818620829
DOI10.1109/FSCS.1990.89560

Cover

More Information
Summary:Results in recursion-theoretic inductive inference have been criticized as depending on unrealistic self-referential examples. J.M. Barzdin (1974) proposed a way of ruling out such examples and conjectured that one of the earliest results of inductive inference theory would fall if his method were used. The author refutes Barzdin's conjecture and proposes a new line of research examining robust separations which are defined using a strengthening of Barzdin's original idea. Preliminary results are presented, and the most important open problem is stated as a conjecture. The extension of this work from function learning to formal language learning is discussed.< >
ISBN:081862082X
9780818620829
DOI:10.1109/FSCS.1990.89560