| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 532401 | Pattern Recognition | 2012 | 9 Pages |
Abstract
⺠We suggest an ensemble tessellation method for non-parametric density estimation. ⺠We introduce a model selection procedure with complexity penalization. ⺠Information-theoretic model selection yields a tessellation estimator with good bias/variance properties. ⺠Simulation studies illustrate the effectiveness of the estimator in one and two dimensions.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Matthew Browne,