Theoretical Properties of Projection Based Multilayer Perceptrons with Functional Inputs
Neural Processing Letters
The Concentration of Fractional Distances
IEEE Transactions on Knowledge and Data Engineering
Classification of gene functions using support vector machine for time-course gene expression data
Computational Statistics & Data Analysis
An extension of Fisher's discriminant analysis for stochastic processes
Journal of Multivariate Analysis
Support vector machine for functional data classification
Neurocomputing
Clustering signals using wavelets
IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
Maximum likelihood ratio test for the stability of sequence of Gaussian random processes
Computational Statistics & Data Analysis
Consistency of functional learning methods based on derivatives
Pattern Recognition Letters
Functional data analysis in shape analysis
Computational Statistics & Data Analysis
Functional classification with margin conditions
COLT'06 Proceedings of the 19th annual conference on Learning Theory
A functional approach to variable selection in spectrometric problems
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Journal of Multivariate Analysis
Discriminative functional analysis of human movements
Pattern Recognition Letters
| Hi-index | 754.84 |
Let X be a random variable taking values in a separable Hilbert space X, with label Y∈{0,1}. We establish universal weak consistency of a nearest neighbor-type classifier based on n independent copies (Xi,Yi) of the pair (X,Y), extending the classical result of Stone to infinite-dimensional Hilbert spaces. Under a mild condition on the distribution of X, we also prove strong consistency. We reduce the infinite dimension of X by considering only the first d coefficients of a Fourier series expansion of each Xi, and then we perform k-nearest neighbor classification in Rd. Both the dimension and the number of neighbors are automatically selected from the data using a simple data-splitting device. An application of this technique to a signal discrimination problem involving speech recordings is presented.