|
Yves Grandvalet
|
Thèmes de RechercheApprentissage supervisé et non superviséReconnaissance de Formes Statistique Régression et discrimination flexible Diagnostic |
Research InterestsSupervised and unsupervised learningStatistical Pattern Recognition Flexible regression/discrimination techniques Fault Diagnosis |
Bengio, Y. & Grandvalet, Y. ``No Unbiased Estimator of the Variance of K-Fold Cros-Validation'', Technical Report 1234, Département d'informatique et recherche opérationnelle, Université de Montréal, 2003.
Grandvalet, Y. & Canu, S. ``Adaptive Scaling for Feature Selection in SVMs'', to appear in Neural Information Processing Systems 2002.
Grandvalet, Y. & Canu, S. ``Outcomes of the equivalence of adaptive ridge with least absolute shrinkage'', in Neural Information Processing Systems, 1998.
Grandvalet, Y. ``Least absolute shrinkage is equivalent to quadratic penalization'', in International Conference on Artificial Neural Networks , 1998.
Boukari, H. & Grandvalet, Y. ``Pénalisation multiple adaptative'', in 13èmes Journées Francophones sur l'Apprentissage, 1998.
Grandvalet, Y. ``Bagging equalizes influence'', Machine Learning, to appear (ps.gz/pdf).
Grandvalet, Y. ``Bagging can stabilize without reducing variance'', in ICANN'01, Lecture Notes in Computer Science, pages 49-56. Springer, 2001.
Grandvalet, Y. ``Bagging down-weights leverage points'', in IJCNN'2000, volume~IV, pages 505--510. IEEE, 2000.
Grandvalet, Y. ``Logistic regression for partial labels'', in 9th International Conference IPMU'02, volume III, pages 1935-1941, 2002.
d'Alché Buc F., Grandvalet Y. & Ambroise, C. ``Semi-supervised MarginBoost'', in 9th Advances in Neural Information Processing Systems 14, pages 553-560. MIT Press, 2002.
Grandvalet Y., d'Alché Buc F. & Ambroise, C. ``Boosting mixture models for semi-supervised learning'', in 9th ICANN'01, Lecture Notes in Computer Science, pages 41-48. Springer, 2001.
François J., Grandvalet Y., Denoeux T. & Roger J.-M. ``Resample and Combine: An Approach to Improving Uncertainty Representation in Evidential Pattern Classification'', Information Fusion Journal, to appear (ps.gz/pdf).
François J., Grandvalet Y., Denoeux T. & Roger J.-M. ``Bagging improves uncertainty representation in evidential pattern classification'', in Technologies for Constructing Intelligent Systems 1 - Tasks, Bouchon-Meunier B., Gutierrez-Rios J., Magdalena L. & Yager R. R. Eds, Physica-Verlag, pages 295-308, 2002.
François J., Grandvalet Y., Denoeux T. & Roger J.-M. ``Bagging belief structures in Dempster-Shafer K-NN rule'', in 8th International Conference IPMU'00, pages 111--118, 2000.
Masson, M. & Grandvalet, Y. ``Réseaux de neurones pour le diagnostic'', in Diagnostic - Intelligence Artificielle et Reconnaissance des Formes, Dubuisson B. Ed, Traité IC2, chapitre 3. Hermès Science, 2001.
Ambroise, C., & Grandvalet Y. ``Prediction of ozone peaks by mixture models'', Ecological Modeling, 145(2/3) : pages 275-289, 2001.
Masson, M. H., Canu, S. & Grandvalet Y. ``Software sensor design based on empirical data'', Ecological Modeling, 120: pages 131-139, 1999.
Canu, S., Ding X. & Grandvalet Y. ``Une application des réseaux de neurones pour la prévision à un pas de temps'', in Statistique et méthodes neuronales, Thiria S., Lechevallier Y., Gascuel O. & Canu S. Eds, chapitre 7. Dunod, 1997.
Grandvalet, Y. & Canu, S. ``Diagnosis of glass quality in a manufacturing process: two connectionist solutions'', in SAFEPROCESS, 1997.
Grandvalet, Y. ``Injection de bruit adaptative pour la détermination de variables pertinentes'', RIA. Systèmes d'apprentissage connexionnistes, 15, pages 351-371, 2001.
Grandvalet, Y. ``Anisotropic noise injection for input variables relevance determination'', IEEE Transactions on Neural Networks, 11(6), pages 1201-1212, 2000.
Grandvalet, Y. & Canu, S. ``Adaptive Noise Injection for Input Variables Relevance Determination'', in International Conference on Artificial Neural Networks, 1997.
Grandvalet, Y., Canu, S. & Boucheron, S. ``Noise Injection: Theoretical Prospects'' , Neural Computation, 9(5), pages 1093-1108, 1997.
Grandvalet, Y. & Canu, S. ``A Comment on Noise Injection into Inputs in Back-Propagation Learning'', IEEE Trans. on Systems, Man and Cybernetics, 25(4), pages 678-681, 1995.
Grandvalet, Y., Canu, S. & Boucheron, S. ``Control of complexity in learning with perturbated inputs'' , in European Symposium on Artificial Neural Networks , pages 167-174, D facto, 1995.
Grandvalet, Y. Injection de bruit dans les perceptrons multicouches. Thèse de Doctorat de l'Université de Technologie de Compiègne, spécialité Contrôle des Systèmes, 1995.Abstract.
Régression logistique pour des étiquettes partielles séminaire DIRO du 14/11/02.
Théorie de l'apprentissage statistique selon Vapnik.
Techniques de rééchantillonnage appliquées à la sélection et à la combinaison de modèles.