Mitotic Classes

For the natural notion of splitting classes into two disjoint subclasses via a recursive classifier working on texts, the question is addressed how these splittings can look in the case of learnable classes. Here the strength of the classes is compared using the strong and weak reducibility from intrinsic complexity. It is shown that, for explanatorily learnable classes, the complete classes are also mitotic with respect to weak and strong reducibility, respectively. But there is a weak complete class which cannot be split into two classes which are of the same complexity with respect to strong reducibility. It is shown that for complete classes for behaviourally correct learning, one half of each splitting is complete for this learning notion as well. Furthermore, it is shown that explanatorily learnable and recursively enumerable classes always have a splitting into two incomparable classes; this gives an inductive inference counterpart of Sacks Splitting Theorem from recursion theory.

[1]  Arun Sharma,et al.  On the intrinsic complexity of language identification , 1994, COLT '94.

[2]  Dana Angluin,et al.  Inductive Inference of Formal Languages from Positive Data , 1980, Inf. Control..

[3]  Richard M. Friedberg,et al.  Three theorems on recursive enumeration. I. Decomposition. II. Maximal set. III. Enumeration without duplication , 1958, Journal of Symbolic Logic.

[4]  John Case,et al.  Machine Inductive Inference and Language Identification , 1982, ICALP.

[5]  Daniel N. Osherson,et al.  Criteria of Language Learning , 1982, Inf. Control..

[6]  Mark A. Fulk Prudence and Other Conditions on Formal Language Learning , 1990, Inf. Comput..

[7]  Marian Boykan Pour-El Review: Gerald E. Sacks, On the Degrees Less than 0' , 1964 .

[8]  Manuel Blum,et al.  Toward a Mathematical Theory of Inductive Inference , 1975, Inf. Control..

[9]  P. Odifreddi Classical recursion theory , 1989 .

[10]  Arun Sharma,et al.  The Structure of Intrinsic Complexity of Learning , 1997, J. Symb. Log..

[11]  Rolf Wiehagen,et al.  Language Learning from Texts: Degrees of Intrinsic Complexity and Their Characterizations , 2000, J. Comput. Syst. Sci..

[12]  Christian Glaßer,et al.  Autoreducibility, mitoticity, and immunity , 2007, J. Comput. Syst. Sci..

[13]  G. Sacks ON THE DEGREES LESS THAN 0 , 1963 .

[14]  Carl H. Smith,et al.  On the Intrinsic Complexity of Learning , 1995, Inf. Comput..

[15]  Klaus Ambos-Spies P-mitotic sets , 1983, Logic and Machines.

[16]  R. Soare Recursively enumerable sets and degrees , 1987 .

[17]  Arun Sharma,et al.  The Intrinsic Complexity of Language Identification , 1996, J. Comput. Syst. Sci..

[18]  Carl H. Smith,et al.  Classifying Predicates and Languages , 1997, Int. J. Found. Comput. Sci..

[19]  Christian Glaßer,et al.  Mitosis in Computational Complexity , 2006, TAMC.

[20]  Richard E. Ladner,et al.  Mitotic recursively enumerable sets , 1973, Journal of Symbolic Logic.

[21]  Emil L. Post Recursively enumerable sets of positive integers and their decision problems , 1944 .

[22]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..