Determination of the Mahalanobis matrix using nonparametric noise estimations
(2006) 14th European Symposium on Artificial Neural Networks (ESANN 2006) — Location: Bruges (Belgium) (26.April.2006)
Files
120-DeterminationoftheMahalanobismatrixusingnonparametricnoiseestimations.pdf
Restricted Access - Adobe PDF
- 1.24 MB
Details
- Authors
- Abstract
- In this paper, the problem of an optimal transformation of the input space for function approximation problems is addressed. The transformationis defined determining the Mahalanobis matrix that minimizesthe variance of noise. To compute variance of the noise, a nonparametricestimator called the Delta Test paradigm is used. The proposed approachis illlustrated on two different benchmarks.
- Affiliations
Helsinky University of Technology Universita di Cagliari Department of Chemical Engineering and Materials
Citations
Lendasse, A., Corona, F., Hao, J., Reyhani, N., & Verleysen, M. (2006). Determination of the Mahalanobis matrix using nonparametric noise estimations. Proceedings of the 14th European Symposium on Artificial Neural Networks (ESANN 2006), p. 227-232. https://hdl.handle.net/2078.5/254143