Expertini Research Research
Artificial Intelligence And Data Science PDF Available Non-peer-reviewed Preprint

Pac-Learning Recursive Logic Programs: Efficient Algorithms

W. W. Cohen  ยท  Published 1995-05-01

Abstract

We present algorithms that learn certain classes of function-free recursive logic programs in polynomial time from equivalence queries. In particular, we show that a single k-ary recursive constant-depth determinate clause is learnable. Two-clause programs consisting of one learnable recursive clause and one constant-depth determinate non-recursive clause are also learnable, if an additional ``basecase'' oracle is assumed. These results immediately imply the pac-learnability of these classes. Although these classes of learnable recursive programs are very constrained, it is shown in a companion paper that they are maximally general, in that generalizing either class in any natural way leads to a computationally difficult learning problem. Thus, taken together with its companion paper, this paper establishes a boundary of efficient learnability for recursive logic programs.
๐Ÿ“„ Full Paper Available as PDF
This paper is available as a downloadable PDF.
๐Ÿ“„ Download PDF

โœจ AI Plain-English Summary

Get a plain-English summary of this paper generated by AI (5 free per day).

Comments (0)

No comments yet. Be the first to comment.

Related Papers

Artificial Intelligence And Data Science PDF

Digital technology, tele-medicine and artificial intelligence in...

2021
Artificial Intelligence And Data Science PDF

Median topographic maps for biomedical data sets

2009
Artificial Intelligence And Data Science PDF

On Planning with Preferences in HTN

2009