Learning Classes Correlated to a Hierarchy
dc.contributor.author | Shih, Lawrence | en_US |
dc.contributor.author | Karger, David | en_US |
dc.date.accessioned | 2004-10-08T20:38:58Z | |
dc.date.available | 2004-10-08T20:38:58Z | |
dc.date.issued | 2003-05-01 | en_US |
dc.identifier.other | AIM-2003-013 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/6719 | |
dc.description.abstract | Trees are a common way of organizing large amounts of information by placing items with similar characteristics near one another in the tree. We introduce a classification problem where a given tree structure gives us information on the best way to label nearby elements. We suggest there are many practical problems that fall under this domain. We propose a way to map the classification problem onto a standard Bayesian inference problem. We also give a fast, specialized inference algorithm that incrementally updates relevant probabilities. We apply this algorithm to web-classification problems and show that our algorithm empirically works well. | en_US |
dc.format.extent | 1146195 bytes | |
dc.format.extent | 480357 bytes | |
dc.format.mimetype | application/postscript | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.relation.ispartofseries | AIM-2003-013 | en_US |
dc.title | Learning Classes Correlated to a Hierarchy | en_US |