H
Huajie Zhang
Researcher at University of Western Ontario
Publications - 10
Citations - 179
Huajie Zhang is an academic researcher from University of Western Ontario. The author has contributed to research in topics: Naive Bayes classifier & Bayesian network. The author has an hindex of 8, co-authored 9 publications receiving 174 citations. Previous affiliations of Huajie Zhang include University of New Brunswick.
Papers
More filters
Book ChapterDOI
An Improved Learning Algorithm for Augmented Naive Bayes
Huajie Zhang,Charles X. Ling +1 more
TL;DR: This work extends Naive Bayes classifier to allow certain dependency relations among attributes, which is more efficient, and produces simpler dependency relation for better comprehensibility, while maintaining very similar predictive accuracy.
Journal ArticleDOI
The representational power of discrete bayesian networks
Charles X. Ling,Huajie Zhang +1 more
TL;DR: This paper establishes an association between the structural complexity of Bayesian networks and their representational power, and uses the maximum number of nodes' parents and the maximum XOR contained in a target function as the measure for the function complexity.
Book ChapterDOI
Toward Bayesian Classifiers with Accurate Probabilities
Charles X. Ling,Huajie Zhang +1 more
TL;DR: AUC provides a more discriminating evaluation for the ranking and probability estimation than the accuracy does, and it is shown that classifiers constructed to maximise the AUC score produce not only higher AUC values, but also higher classification accuracies.
Book ChapterDOI
The Learnability of Naive Bayes
TL;DR: This work gives necessary and sufficient conditions on linearly separable functions in the binary domain to be learnable by Naive Bayes under uniform representation and shows that the learnability (and error rates) of Naïve Bayes can be affected dramatically by sampling distributions.
Proceedings ArticleDOI
Mining generalized query patterns from web logs
TL;DR: A data-mining approach is proposed that produces generalized query patterns or templates from the raw user logs of a popular commercial knowledge-based search engine that is currently in use and shows that such templates can improve search engine's speed and precision.