An efficient approach for finding the MPE in belief networks

@inproceedings{Li1993AnEA,
  title={An efficient approach for finding the MPE in belief networks},
  author={Zhaoyu Li and Bruce D'Ambrosio},
  booktitle={UAI},
  year={1993}
}
Given a belief network with evidence, the task of finding the l most probable ex­ planations (MPE) in the belief network is that of identifying and ordering the l most probable instantiations of the non-evidence nodes of the belief network. Although many approaches have been proposed for solving this problem, most work only for restricted topologies (i.e., singly connected belief net­ works). In this paper, we will present a new approach for finding l MPEs in an arbitrary belief network. First… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.
12 Citations
12 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 12 references

A fast algorithm for finding the k most probable states of the world in bayesian net­ works

  • J. L. Golmard
  • The Thirteeh International Joint Confer­ ence on…
  • 1992
1 Excerpt

Applications of a general propa­ gation algorithm for probabilistic expert systems

  • A. P. Dawid
  • Statistics and Computing,
  • 1992

Dynamic MPA calculations for abduction

  • E. Charniak, Santos E.
  • In Proceedings, Tenth National Conference on AI,
  • 1992
1 Excerpt

On the generation of alternative explanations with implications for belief revision

  • E. Jr Santos
  • Proceedings of the Seventh Conference on Un…
  • 1991

Qualitative propaga­ tion and scenario-based explanation of probabilis­ tic reasoning

  • M. Henrion, M. Druzdel
  • In Proceedings of the Sixth Confer­ ence on…
  • 1990
1 Excerpt

Cost-based abduction and linear constraint satisfaction

  • E. Jr Santos
  • Technical report, Tech Re­ port CS-91-13,
  • 1989
1 Excerpt

Similar Papers

Loading similar papers…