Generative Modeling with Failure in PRISM

  title={Generative Modeling with Failure in PRISM},
  author={Taisuke Sato and Yoshitaka Kameya and Neng-Fa Zhou},
PRISM is a logic-based Turing-complete symbolicstatistical modeling language with a built-in parameter learning routine. In this paper,we enhance the modeling power of PRISM by allowing general PRISM programs to fail in the generation process of observable events. Introducing failure extends the class of definable distributions but needs a generalization of the semantics of PRISM programs. We propose a three valued probabilistic semantics and show how failure enables us to pursue constraint… CONTINUE READING
Highly Cited
This paper has 67 citations. REVIEW CITATIONS


Publications citing this paper.

67 Citations

Citations per Year
Semantic Scholar estimates that this publication has 67 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 16 references

A dynamic programming approach to parameter learning of generative models with failure

  • T. Sato, Y. Kameya
  • Proceedings of ICML 2004 workshop on Learning…
  • 2004
Highly Influential
4 Excerpts

In Proceedings of the Sixth ACM-SIGPLAN International Conference on Principles and Practice of Declarative Programming (PPDP2004)

  • Neng-Fa Zhou, Y. Shen, T. Sato. Semi-naive Evaluation in Linear Tabling
  • pages 90–97,
  • 2004
3 Excerpts


  • J. Cussens. Parameter estimation in stochastic logic Learning
  • Sept.
  • 2001
2 Excerpts

Similar Papers

Loading similar papers…