Functional preprocessing for multilayer perceptrons

In many applications, high dimensional input data can be considered as sampled functions. We show in this paper how to use this prior knowledge to implement functional preprocessings that allow to consistently reduce the dimension of the data even when they have missing values. Preprocessed functions are then handled by a numerical MLP which approximates the theoretical functional MLP. A successful application to spectrometric data is proposed to illustrate the method.

• Type: Conference
• Year: 2004
• Where: ESANN
• Authors: Fabrice Rossi, Brieuc Conan-Guez
• Keywords: Dimensional Input Data, ESANN 2004, ESANN 2007, Numerical Mlp, Theoretical Functional Mlp