Ranking a Random Feature For Variable And Feature Selection

Ranking a Random Feature For Variable And Feature Selection (2003)

Cached

Download Links

[www.jmlr.org]

Other Repositories/Bibliography

DBLP

by Hervé Stoppiglia , Gérard Dreyfus , Rémi Dubois , Yacine Oussar

Venue:	JOURNAL OF MACHINE LEARNING RESEARCH 3 (2003) 1399-1414
Citations:	28 - 5 self

BibTeX

@MISC{Stoppiglia03rankinga,
    author = {Hervé Stoppiglia and Gérard Dreyfus and Rémi Dubois and Yacine Oussar},
    title = {Ranking a Random Feature For Variable And Feature Selection},
    year = {2003}
}

Bookmark

OpenURL

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.

Citations

474	Gene selection for cancer classification using support vector machines - Guyon, Weston, et al. - 2002
210	Orthogonal least squares learning algorithm for radial basis function networks,IEE Trans Neural Networks,2:302-309(1991 - Chen, CFN, et al.
169	Pruning algorithms ± a survey - Reed - 1993
164	Introduction to the Theory of Statistics - Mood, Graybill, et al. - 1974
164	Classical and Modern Regression with Applications. 2nd ed - Myers - 1990
163	Feature Selection for SVMs - Weston, Mukherjee, et al. - 2000
102	Orthogonal least squares methods and their application to non-linear system identification - Chen, Billings, et al. - 1989
48	Kernel matching pursuit - Vincent, Bengio
12	Model selection and validation methods for non-linear systems - Leontaritis, Billings - 1999
12	Local Overfitting Control via Leverages - Monari, Dreyfus
8	G: Withdrawing an example from the training set: an analytic estimation of its effect on a nonlinear parameterized model. Neurocomputing 2000, 35(1-4):195-201. et al - Monari, Dreyfus
6	Towards a principled methodology for neural network design and performance evaluation in qsar; application to the prediction of logp - Duprat, Huynh, et al. - 1998
6	Initialization by selection for wavelet network training - Oussar, Dreyfus
6	Two-step feature selection and neural network classification for the trec-8 routing - Stricker, Vichot, et al. - 1999
4	Descriptor generation, selection and model building in quantitative structure-property analysis - Breneman, Bennett, et al. - 2002
4	R eseaux de neurones pour le traitement automatique du langage : conception et r ealisation de filtres d'informations - Stricker - 2000
4	The selection of neural models of nonlinear dynamical systems by statistical tests - Urbani, Roussel-Ragot, et al. - 1993
2	Solving linear least squares problems by gram-schmidt orthogonalization. Nordisk Tidshrift for Informationsbehadlung, 7:1--21 - Bjoerck - 1967
2	Information retrieval based on context distance and morphology - Society - 1995
2	A new decision criterion for feature selection: Application to the classification of non destructive testing signatures - Oukhellou, Aknin, et al. - 1998
2	On model structure testing in system identification - Soederstroem - 1977
1	election de mod eles non lin eaires par leave-one-out. Etude th eorique et application au proc ed e de soudage par points - unknown authors - 1999
1	eseaux d'ondelettes et r eseaux de neurones pour la mod elisation statique et dynamique de processus - unknown authors - 1998
1	M ethodes Statistiques de S election de Mod eles Neuronaux ; Applications Financi eres et Bancaires - STOPPIGLIA, DUBOIS, et al. - 1997