---
title: "Avoiding Pitfalls When Learning Recursive Theories"
authors:
  - "R. Mike Cameron-Jones"
  - "J. Ross Quinlan"
doi: ""
url: "https://ijcai.org/proceedings/1993/145"
pdf: "https://ijcai.org/proceedings/1993/0145.pdf"
venue: "Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence"
year: 1993
pages: "1050-1056"
track: "Machine Learning"
keywords:
---

# Avoiding Pitfalls When Learning Recursive Theories

R. Mike Cameron-Jones, J. Ross Quinlan

*Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence*, pages 1050-1056.

## Abstract

Learning systems that express theories in firstorder logic must ensure that the theories are executable and, in particular, that they do not lead to infinite recursion . This paper presents a heuristic method for preventing infinite recursion in the (multi-clause) definition of a recursive relation. The method has been implemented in the latest version of FOIL, but could also be used with any learning method that grows clauses from ground facts by repeated specialization. Results on several examples, including Ackermann's function, are presented .