Enlarging learnable classes

We study which classes of recursive functions satisfy that their union with any other explanatorily learnable class of recursive functions is again explanatorily learnable. We provide sufficient criteria for classes of recursive functions to satisfy this property and also investigate its effective variants. Furthermore, we study the question which learners can be effectively extended to learn a larger class of functions. We solve an open problem by showing that there is no effective procedure which does this task on all learners which do not learn a dense class of recursive functions. However, we show that there are two effective extension procedures such that each learner is extended by one of them.

[1]  Mark A. Fulk,et al.  Maximal Machine Learnable Classes , 1999, J. Comput. Syst. Sci..

[2]  John Case,et al.  On the classification of recursive languages , 2004, Inf. Comput..

[3]  Jr. Hartley Rogers Theory of Recursive Functions and Effective Computability , 1969 .

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

[5]  Stuart A. Kurtz,et al.  Extremes in the Degrees of Inferability , 1994, Ann. Pure Appl. Log..

[6]  John Case,et al.  Periodicity in generations of automata , 1974, Mathematical systems theory.

[7]  Rusins Freivalds,et al.  Closedness properties in ex-identification , 2001, Theor. Comput. Sci..

[8]  Frank Stephan,et al.  On one-sided versus two-sided classification , 2001, Arch. Math. Log..

[9]  Sanjay Jain,et al.  Enlarging Learnable Classes , 2012, ALT.

[10]  Eliana Minicozzi,et al.  Some Natural Properties of Strong-Identification in Inductive Inference , 1976, Theor. Comput. Sci..

[11]  Thomas Zeugmann,et al.  Learning recursive functions: A survey , 2008, Theor. Comput. Sci..

[12]  Leonard Pitt,et al.  Inductive Inference, DFAs, and Computational Complexity , 1989, AII.

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

[14]  John Case,et al.  Refinements of inductive inference by Popperian and reliable machines , 1994, Kybernetika.

[15]  Frank Stephan,et al.  On the structure of degrees of inferability , 1993, COLT '93.

[16]  Daniel N. Osherson,et al.  Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists , 1990 .

[17]  D. C. Cooper,et al.  Theory of Recursive Functions and Effective Computability , 1969 .

[18]  Manuel Blum,et al.  Inductive inference and unsolvability , 1991, Journal of Symbolic Logic.

[19]  John Case,et al.  Comparison of Identification Criteria for Machine Inductive Inference , 1983, Theor. Comput. Sci..