Multilayer Perceptron with Functional Inputs: an Inverse Regression Approach
Statistics Theory
2007-05-23 v1 Statistics Theory
Abstract
Functional data analysis is a growing research field as more and more practical applications involve functional data. In this paper, we focus on the problem of regression and classification with functional predictors: the model suggested combines an efficient dimension reduction procedure [functional sliced inverse regression, first introduced by Ferr\'e & Yao (Statistics, 37, 2003, 475)], for which we give a regularized version, with the accuracy of a neural network. Some consistency results are given and the method is successfully confronted to real-life data.
Cite
@article{arxiv.0705.0211,
title = {Multilayer Perceptron with Functional Inputs: an Inverse Regression Approach},
author = {Louis Ferré and Nathalie Villa},
journal= {arXiv preprint arXiv:0705.0211},
year = {2007}
}