Abstract | ||
---|---|---|
We describe a feature selection method that can be applied directly to models that are linear with respect to their parameters, and indirectly to others. It is independent of the target machine. It is closely related to classical statistical hypothesis tests, but it is more intuitive, hence more suitable for use by engineers who are not statistics experts. Furthermore, some assumptions of classical tests are relaxed. The method has been used successfully in a number of applications that are briefly described. |
Year | Venue | Keywords |
---|---|---|
2003 | Journal of Machine Learning Research | feature selection,gram-schmidt orthogonalization,random feature,feature selection method,leave-one-out,kernel,model selection,classical statistical hypothesis test,classical test,statistics expert,classification,neural networks,statistical tests,information filtering,target machine,variable selection,neural network,statistical test,statistical hypothesis testing |
Field | DocType | Volume |
Feature selection,Pattern recognition,Ranking,Artificial intelligence,Mathematics,Machine learning,Statistical hypothesis testing | Journal | 3, |
Citations | PageRank | References |
92 | 10.26 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hervé STOPPIGLIA | 1 | 96 | 11.65 |
Gérard Dreyfus | 2 | 475 | 58.97 |
Rémi Dubois | 3 | 146 | 23.45 |
Y. Oussar | 4 | 294 | 26.32 |