Adaptive matrix distances aiming at optimum regression subspaces

M. Strickert; Axel J. Soto; Gustavo E. Vazquez

Adaptive matrix distances aiming at optimum regression subspaces

M. Strickert, Axel J. Soto, Gustavo E. Vazquez

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

6 Citas (Scopus)

Resumen

A new supervised adaptive metric approach is introduced for mapping an input vector space to a plottable low-dimensional subspace in which the pairwise distances are in maximum correlation with distances of the associated target space. The new formalism of multivariate subspace regression (MSR) is based on cost function optimization, and it allows assessing the relevance of input vector attributes. An application to molecular descriptors in a chemical compound database is presented for targeting octanol-water partitioning properties.

Idioma original	Inglés
Título de la publicación alojada	Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010
Páginas	93-98
Número de páginas	6
Estado	Publicada - 2010
Publicado de forma externa	Sí
Evento	18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2010 - Bruges Duración: 28 abr. 2010 → 30 abr. 2010

Serie de la publicación

Nombre	Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010

Conferencia

Conferencia	18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2010
País/Territorio	Belgium
Ciudad	Bruges
Período	28/04/10 → 30/04/10

Otros archivos y enlaces

http://www.scopus.com/inward/record.url?scp=84886999438&partnerID=8YFLogxK

Citar esto

Strickert, M., Soto, A. J., & Vazquez, G. E. (2010). Adaptive matrix distances aiming at optimum regression subspaces. En Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010 (pp. 93-98). (Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010).

Strickert, M. ; Soto, Axel J. ; Vazquez, Gustavo E. / Adaptive matrix distances aiming at optimum regression subspaces. Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010. 2010. pp. 93-98 (Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010).

@inproceedings{00044a170e594ff3bd272397cf674070,

title = "Adaptive matrix distances aiming at optimum regression subspaces",

abstract = "A new supervised adaptive metric approach is introduced for mapping an input vector space to a plottable low-dimensional subspace in which the pairwise distances are in maximum correlation with distances of the associated target space. The new formalism of multivariate subspace regression (MSR) is based on cost function optimization, and it allows assessing the relevance of input vector attributes. An application to molecular descriptors in a chemical compound database is presented for targeting octanol-water partitioning properties.",

keywords = "Data-driven metric, Feature rating, Informative subspace",

author = "M. Strickert and Soto, {Axel J.} and Vazquez, {Gustavo E.}",

year = "2010",

language = "Ingl{\'e}s",

isbn = "2930307102",

series = "Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010",

pages = "93--98",

booktitle = "Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010",

note = "18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2010 ; Conference date: 28-04-2010 Through 30-04-2010",

}

Strickert, M, Soto, AJ & Vazquez, GE 2010, Adaptive matrix distances aiming at optimum regression subspaces. En Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010. Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010, pp. 93-98, 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2010, Bruges, Belgium, 28/04/10.

Adaptive matrix distances aiming at optimum regression subspaces. / Strickert, M.; Soto, Axel J.; Vazquez, Gustavo E.
Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010. 2010. p. 93-98 (Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución a la conferencia › revisión exhaustiva

TY - GEN

T1 - Adaptive matrix distances aiming at optimum regression subspaces

AU - Strickert, M.

AU - Soto, Axel J.

AU - Vazquez, Gustavo E.

PY - 2010

Y1 - 2010

N2 - A new supervised adaptive metric approach is introduced for mapping an input vector space to a plottable low-dimensional subspace in which the pairwise distances are in maximum correlation with distances of the associated target space. The new formalism of multivariate subspace regression (MSR) is based on cost function optimization, and it allows assessing the relevance of input vector attributes. An application to molecular descriptors in a chemical compound database is presented for targeting octanol-water partitioning properties.

AB - A new supervised adaptive metric approach is introduced for mapping an input vector space to a plottable low-dimensional subspace in which the pairwise distances are in maximum correlation with distances of the associated target space. The new formalism of multivariate subspace regression (MSR) is based on cost function optimization, and it allows assessing the relevance of input vector attributes. An application to molecular descriptors in a chemical compound database is presented for targeting octanol-water partitioning properties.

KW - Data-driven metric

KW - Feature rating

KW - Informative subspace

UR - http://www.scopus.com/inward/record.url?scp=84886999438&partnerID=8YFLogxK

M3 - Contribución a la conferencia

AN - SCOPUS:84886999438

SN - 2930307102

SN - 9782930307107

T3 - Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010

SP - 93

EP - 98

BT - Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010

T2 - 18th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2010

Y2 - 28 April 2010 through 30 April 2010

ER -

Strickert M, Soto AJ, Vazquez GE. Adaptive matrix distances aiming at optimum regression subspaces. En Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010. 2010. p. 93-98. (Proceedings of the 18th European Symposium on Artificial Neural Networks - Computational Intelligence and Machine Learning, ESANN 2010).

Adaptive matrix distances aiming at optimum regression subspaces

Resumen

Serie de la publicación

Conferencia

Otros archivos y enlaces

Huella

Citar esto