Comparing Methods for Refining Certainty-Factor Rule-Bases

@inproceedings{Mahoney1994ComparingMF,
  title={Comparing Methods for Refining Certainty-Factor Rule-Bases},
  author={J. Jeffrey Mahoney and Raymond J. Mooney},
  booktitle={ICML},
  year={1994}
}
This paper compares two methods for re ning uncertain knowledge bases using propositional certainty-factor rules. The rst method, implemented in the Rapture system, employs neural-network training to rene the certainties of existing rules but uses a symbolic technique to add new rules. The second method, based on the one used in the Kbann system, initially adds a complete set of potential new rules with very low certainty and allows neural-network training to lter and adjust these rules… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 30 references

Probabilistic Revision of Logical Domain Theories

  • R. Feldman
  • PhD thesis, Department of Computer Science…
  • 1993
1 Excerpt

Node error assignment in expert networks

  • R. Lacher
  • Kandel, A., and Langholz, G., editors, Hybrid…
  • 1992
2 Excerpts

Similar Papers

Loading similar papers…