Machine learning of higher-order programs

A generator program for a computable function (by definition) generates an infinite sequence of programs all but finitely many of which compute that function. Machine learning of generator programs for computable functions is studied. To partially motivate these studies, it is shown that, in some cases, interesting global properties for computable functions can be proved from suitable generator programs which can not be proved from any ordinary programs for them. The power (for variants of various learning criteria from the literature) of learning generator programs is compared with the power of learning ordinary programs. The learning power in these cases is also compared to that of learning limiting programs, i.e., programs allowed finitely many mind changes about their correct outputs.

[1]  Elliott Mendelson,et al.  Introduction to Mathematical Logic , 1979 .

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

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

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

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

[6]  John Case,et al.  On Learning Limiting Programs , 1992, Int. J. Found. Comput. Sci..

[7]  Arto Salomaa,et al.  ICALP'88: Proceedings of the 15th International Colloquium on Automata, Languages and Programming , 1988 .

[8]  Hilary Putnam,et al.  Trial and error predicates and the solution to a problem of Mostowski , 1965, Journal of Symbolic Logic.

[9]  Joseph R. Shoenfield,et al.  Degrees of unsolvability , 1959, North-Holland mathematics studies.

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

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

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

[13]  Patrick C. Fischer.  Theory of provable recursive functions , 1965 .

[14]  William Craig,et al.  On axiomatizability within a system , 1953, Journal of Symbolic Logic.

[15]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[16]  S. Feferman.  Arithmetization of metamathematics in a general setting , 1959 .

[17]  Keh-Jiann Chen,et al.  Tradeoffs in machine inductive inference , 1981 .

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

[19]  N. Shapiro.  Review: E. Mark Gold, Limiting Recursion; Hilary Putnam, Trial and Error Predicates and the Solution to a Problem of Mostowski , 1971 .

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

[21]  Carl H. Smith,et al.  Inductive Inference: Theory and Methods , 1983, CSUR.

[22]  Georg Kreisel,et al.  On the interpretation of non-finitist proofs—Part I , 1951, Journal of Symbolic Logic.

[23]  Georg Kreisel,et al.  Mathematical significance of consistency proofs , 1958, Journal of Symbolic Logic.

[24]  H. E. Rose.  Subrecursion: Functions and Hierarchies , 1984 .

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

[26]  Rolf Wiehagen,et al.  Research in the theory of inductive inference by GDR mathematicians - A survey , 1980, Inf. Sci..

[27]  Mark A. Fulk.  A study of inductive inference machines , 1986 .

[28]  N. A. Lynch.  RELATIVIZATION OF THE THEORY OF COMPUTATION COMPLEXITY , 1972 .