An Empirical Analysis of Likelihood-Weighting Simulation on a Large, Multiply-Connected Belief Network
M Shwe, GF Cooper - arXiv preprint arXiv:1304.1141, 2013 - arxiv.org
M Shwe, GF Cooper
arXiv preprint arXiv:1304.1141, 2013•arxiv.orgWe analyzed the convergence properties of likelihood-weighting algorithms on a two-level,
multiply connected, belief-network representation of the QMR knowledge base of internal
medicine. Specifically, on two difficult diagnostic cases, we examined the effects of Markov
blanket scoring, importance sampling, demonstrating that the Markov blanket scoring and
self-importance sampling significantly improve the convergence of the simulation on our
model.
multiply connected, belief-network representation of the QMR knowledge base of internal
medicine. Specifically, on two difficult diagnostic cases, we examined the effects of Markov
blanket scoring, importance sampling, demonstrating that the Markov blanket scoring and
self-importance sampling significantly improve the convergence of the simulation on our
model.
We analyzed the convergence properties of likelihood- weighting algorithms on a two-level, multiply connected, belief-network representation of the QMR knowledge base of internal medicine. Specifically, on two difficult diagnostic cases, we examined the effects of Markov blanket scoring, importance sampling, demonstrating that the Markov blanket scoring and self-importance sampling significantly improve the convergence of the simulation on our model.
arxiv.org