Journal of Symbolic Logic

Machine Learning of Higher-Order Programs

Ganesh Baliga, John Case, Sanjay Jain, and Mandayam Suraj

Full-text is available via JSTOR, for JSTOR subscribers. Go to this article in JSTOR.


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 motivate these studies partially, it is shown that, in some cases, interesting global properties for computable functions can be proved from suitable generator programs which cannot 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.

Article information

J. Symbolic Logic, Volume 59, Issue 2 (1994), 486-500.

First available in Project Euclid: 6 July 2007

Permanent link to this document

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier



Baliga, Ganesh; Case, John; Jain, Sanjay; Suraj, Mandayam. Machine Learning of Higher-Order Programs. J. Symbolic Logic 59 (1994), no. 2, 486--500.

Export citation