Consistent Partial Identification

This study contrasts consistent partial identification with learning in the limit. Here partial identification means that the learner outputs an infinite sequence of conjectures in which one correct hypothesis occurs infinitely often and all other hypotheses occur only finitely often. Consistency means that every conjecture is correct on all the data seen so far. Learning in the limit means that the learner outputs from some time on always the same correct hypothesis. As the class of all total-recursive functions can be partially identified, the constraint of consistency has to be added to make a meaningful comparison to learning in the limit. For the version of consistency where the learner has to be defined and consistent on all inputs, it is shown that the power of the learning criterion depends on whether the function to be learnt is fed in canonical order or in arbitrary order. In the first case, consistent partial identification is incomparable to learning in the limit; in the second case, it is equivalent to consistent learning in the limit with arbitrarily fed input. Furthermore, the inference degrees of these criteria are investigated. For the case where the function is fed in canonical order, there are just two inference degrees: the trivial one which contains all oracles of hyperimmune free Turing degree and the omniscient one which contains all oracles of hyperimmune Turing degree. In the case that the function is fed in arbitrary order, the picture is more complicated and the omniscient inference degree contains exactly all oracles of high Turing degree.

[1]  Robert I. Soare,et al.  Recursively enumerable sets and degrees - a study of computable functions and computability generated sets , 1987, Perspectives in mathematical logic.

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

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

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

[5]  William I. Gasarch,et al.  Learning via queries to an oracle , 1989, COLT '89.

[6]  Donald A. Martin,et al.  Classes of Recursively Enumerable Sets and Degrees of Unsolvability , 1966 .

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

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

[9]  D. C. Cooper,et al.  Theory of Recursive Functions and Effective Computability , 1969, The Mathematical Gazette.

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

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

[12]  Klaus P. Jantke,et al.  Combining Postulates of Naturalness in Inductive Inference , 1981, J. Inf. Process. Cybern..

[13]  Gunter Grieser Reflective inductive inference of recursive functions , 2008, Theor. Comput. Sci..

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

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

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

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

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

[19]  Steffen Lange,et al.  Algorithmic Learning for Knowledge-Based Systems: Gosler Final Report , 1995 .

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

[21]  Gunter Grieser Reflective Inductive Inference of Recursive Functions , 2002, ALT.

[22]  Manuel Blum,et al.  A Machine-Independent Theory of the Complexity of Recursive Functions , 1967, JACM.

[23]  Robert H. Sloan,et al.  BOOK REVIEW: "SYSTEMS THAT LEARN: AN INTRODUCTION TO LEARNING THEORY, SECOND EDITION", SANJAY JAIN, DANIEL OSHERSON, JAMES S. ROYER and ARUN SHARMA , 2001 .