Avoiding Pitfalls When Learning Recursive Theories

Cameron-Jones, R. Mike; Quinlan, J. Ross

Avoiding Pitfalls When Learning Recursive Theories

Download BibTeX Cite

Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence. Machine Learning. 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 .

R. Mike Cameron-Jones, and J. Ross Quinlan. 1993. Avoiding Pitfalls When Learning Recursive Theories. In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, IJCAI-93. IJCAI, 1050–1056. https://ijcai.org/proceedings/1993/145

@inproceedings{ijcai1993p145,
  title     = {Avoiding Pitfalls When Learning Recursive Theories},
  author    = {Cameron-Jones, R. Mike and Quinlan, J. Ross},
  booktitle = {Proceedings of the Thirteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-93}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Ruzena Bajcsy},
  pages     = {1050--1056},
  year      = {1993},
  note      = {Machine Learning},
  url       = {https://ijcai.org/proceedings/1993/145},
}

TY  - CPAPER
TI  - Avoiding Pitfalls When Learning Recursive Theories
AU  - Cameron-Jones, R. Mike
AU  - Quinlan, J. Ross
T2  - Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, IJCAI-93
PB  - International Joint Conferences on Artificial Intelligence
PY  - 1993
SP  - 1050
EP  - 1056
UR  - https://ijcai.org/proceedings/1993/145
ER  -