Space-Efficient Inference in Dynamic Probabilistic Networks

  title={Space-Efficient Inference in Dynamic Probabilistic Networks},
  author={John Binder and Kevin P. Murphy and Stuart J. Russell},
Dynamic probabilistic networks (DPNs) are a useful tool for modeling complex stochastic processes. The simplest inference task in DPNs is monitoring | that is, computing a posterior distribution for the state variables at each time step given all observations up to that time. Recursive, constant-space algorithms are well-known for monitoring in DPNs and other models. This paper is concerned with hind-sight | that is, computing a posterior distribution given both past and future observations… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.

Bayesian updatingin causal probabilistic networks by local computations

  • Finn V. Jensen, Ste en L. Lau, Kristian G. Olesen
  • Computational Statistics Quarterly
  • 1995

Locallearning in probabilistic networks with hidden variables

  • JohnBinder Stuart Russell
  • 1995

A new approach to linear ltering and prediction problems

  • R. E. Kalman
  • Journal of BasicEngineering , pages
  • 1990

Similar Papers

Loading similar papers…