Numberings optimal for learning

This paper extends previous studies on learnability in non-acceptable numberings by considering the question: for which criteria which numberings are optimal, that is, for which numberings it holds that one can learn every learnable class using the given numbering as hypothesis space. Furthermore an effective version of optimality is studied as well. It is shown that the effectively optimal numberings for finite learning are just the acceptable numberings. In contrast to this, there are non-acceptable numberings which are optimal for finite learning and effectively optimal for explanatory, vacillatory and behaviourally correct learning. The numberings effectively optimal for explanatory learning are the K-acceptable numberings. A similar characterization is obtained for the numberings which are effectively optimal for vacillatory learning. Furthermore, it is studied which numberings are optimal for one and not for another criterion: among the criteria of finite, explanatory, vacillatory and behaviourally correct learning all separations can be obtained; however every numbering which is optimal for explanatory learning is also optimal for consistent learning.

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

[2]  Rolf Wiehagen,et al.  Learning and Consistency , 1995, GOSLER Final Report.

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

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

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

[6]  Sandra Zilles,et al.  Increasing the power of uniform inductive learners , 2005, J. Comput. Syst. Sci..

[7]  John Case,et al.  The Power of Vacillation in Language Learning , 1999, SIAM J. Comput..

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

[9]  John Case,et al.  Control structures in hypothesis spaces: the influence on learning , 2002, Theor. Comput. Sci..

[10]  Sandra Zilles.  Separation of uniform learning classes , 2004, Theor. Comput. Sci..

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

[12]  Rusins Freivalds,et al.  Inductive Inference and Computable One-One Numberings , 1982, Math. Log. Q..

[13]  Sanjay Jain,et al.  Learning in Friedberg numberings , 2008, Inf. Comput..

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

[15]  Rolf Wiehagen,et al.  Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen , 1976, J. Inf. Process. Cybern..

[16]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

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

[18]  Dick de Jongh,et al.  Angluin's theorem for indexed families of r.e. sets and applications , 1996, COLT '96.

[19]  Arun Sharma,et al.  Learning with the Knowledge of an Upper Bound on Program Size , 1993, Inf. Comput..

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

[21]  Thomas Zeugmann,et al.  Language learning in dependence on the space of hypotheses , 1993, COLT '93.

[22]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.