N
Nevin L. Zhang
Researcher at Hong Kong University of Science and Technology
Publications - 195
Citations - 5056
Nevin L. Zhang is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Bayesian network & Latent variable. The author has an hindex of 30, co-authored 176 publications receiving 4668 citations. Previous affiliations of Nevin L. Zhang include Peking University & Aalborg University.
Papers
More filters
Journal ArticleDOI
Exploiting causal independence in Bayesian network inference
Nevin L. Zhang,David Poole +1 more
TL;DR: A notion of causal independence is presented that enables one to further factorize the conditional probabilities into a combination of even smaller factors and consequently obtain a finer-grain factorization of the joint probability.
Proceedings Article
Incremental pruning: a simple, fast, exact method for partially observable Markov decision processes
TL;DR: It is found that incremental pruning is presently the most efficient exact method for solving POMDPS.
Posted Content
Exploiting Causal Independence in Bayesian Network Inference
Nevin L. Zhang,David Poole +1 more
TL;DR: In this article, the authors proposed a new method for exploiting causal independencies in exact Bayesian network inference, which enables one to further factorize the conditional probabilities into a combination of even smaller factors and consequently obtain a finer-grain factorization of the joint probability.
Proceedings Article
A simple approach to Bayesian network computations
Nevin L. Zhang,David Poole +1 more
TL;DR: A new approach is proposed which adopts a straightforward way for facilitating joint probabilities and allows the pruning of irrelevant variables and changes to the knowledge base more easily, and can be adapted to utilize both intercausal independence and condi tional independence in one uniform frame work.
Journal ArticleDOI
Hierarchical Latent Class Models for Cluster Analysis
TL;DR: A search-based algorithm for learning hierarchical latent class models from data using a framework where the local dependence problem can be addressed in a principled manner is developed.