M
Michael J. Pazzani
Researcher at University of California, Riverside
Publications - 190
Citations - 29519
Michael J. Pazzani is an academic researcher from University of California, Riverside. The author has contributed to research in topics: Explanation-based learning & Stability (learning theory). The author has an hindex of 62, co-authored 183 publications receiving 28036 citations. Previous affiliations of Michael J. Pazzani include University of California & Rutgers University.
Papers
More filters
Journal ArticleDOI
Application of an expert system in the management of HIV-infected patients
TL;DR: The CTSHIV system couples efficient genetic sequencing with an expert program that recommends regimens based on information in the current medical literature to serve as a useful tool in the design of clinical trials and in the management of HIV-infected patients.
Book ChapterDOI
The Independent Sign Bias: Gaining Insight from Multiple Linear Regression
TL;DR: Some factors that influence whether the resulting regression equation is a credible model of the relationship between a set of explanatory variables and a dependent variable by fitting a linear equation to observed data are investigated and discussed.
Journal ArticleDOI
Ghost Imputation: Accurately Reconstructing Missing Data of the Off Period
TL;DR: An accurate and efficient algorithm for missing data reconstruction (imputation), that is specifically designed to recover off-period segments of missing data, and introduces a caching approach that reduces the search space and improves the computational complexity to linear in the common case.
Reducing the small disjuncts problem by learning probabilistic concept descriptions
Kamal A. Ali,Michael J. Pazzani +1 more
TL;DR: Ali et al. as mentioned in this paper presented a method for learning relational and attribute-value concepts based on maximum-likelihood estimation, which reduces the contribution of error from small disjuncts.
Proceedings ArticleDOI
Generating models of mental retardation from data with machine learning
TL;DR: The study shows that the KDD methods hold promise in recovering useful structure from medical data and identified emotional/behavioral problems in children as a significant predictor of MR risk.