PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Input selection and function approximation using the SOM: an application to spectrometric modeling
Francesco Corona and Amaury Lendasse
In: WSOM'05, 5th Workshop on Self-Organizing Maps, 5-8 September 2005, Paris 1 Panthéon-Sorbonne University, Paris, France.


This paper presents a global methodology to build a nonlinear regression when the number of available samples is small compared to the number of inputs. The task is divided in two parts: selection of the best inputs and construction of the approximator. A first SOM is used to compute clean correlations between the inputs and the output. A second SOM is built to link the output to the selected inputs. The good performances of this methodology are illustrated on a spectrometric dataset.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:1686
Deposited By:Amaury Lendasse
Deposited On:28 November 2005