Learning-theoretic perspectives of acceptable numberings

A class of recursive functionsC islimiting standardizable, in a programming system φ, iff there is an effective procedure which, given any φ-program (in the φ-system), synthesizes in the limit acanonical φ-program which is equivalent to the former. It can arguably be expected that notions similar to the above one would be relevant toGold-style function learning, which features, among other things, the effective limiting synthesis of programs for input recursive functions. Many learning classes have been characterized in terms of variants of the above notion. In this paper, we focus on the limiting standardizability of the entire class of recursive functions inEffective programming systems. To start with, we prove the independence of this notionvis-à-vis finitary recursion theorems. Secondly, we show that this motion does not entail acceptability, in the spirit of the results of Case, Riccardi and Royer on characterizations of the samevis-à-vis programming language control structures.

[1]  John Case,et al.  Infinitary self-reference in learning theory , 1994, J. Exp. Theor. Artif. Intell..

[2]  James S. Royer A Connotational Theory of Program Structure , 1987, Lecture Notes in Computer Science.

[3]  Martin Kummer An Easy Priority-Free Proof of a Theorem of Friedberg , 1990, Theor. Comput. Sci..

[4]  K. Popper,et al.  Conjectures and refutations;: The growth of scientific knowledge , 1972 .

[5]  Paul Young,et al.  An introduction to the general theory of algorithms , 1978 .

[6]  R. V. Freivald Minimal Gödel Numbers and Their Identification in the Limit , 1975, MFCS.

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

[8]  Gregory A. Riccardi The Independence of Control Structures in Abstract Programming Systems , 1981, J. Comput. Syst. Sci..

[9]  Hartley Rogers,et al.  Gödel numberings of partial recursive functions , 1958, Journal of Symbolic Logic.

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

[11]  Marian Boykan Pour-El Gödel numberings versus Friedberg numberings , 1964 .

[12]  K. Popper,et al.  The Logic of Scientific Discovery , 1960 .

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

[14]  John Case,et al.  Strong separation of learning classes , 1992, J. Exp. Theor. Artif. Intell..

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

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

[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]  Rusins Freivalds,et al.  Connections between Identifying Functionals, standardizing Operations, and Computable Numberings , 1984, Math. Log. Q..