Non-Negative Pre-Image in Machine Learning for Pattern Recognition
Résumé
Moreover, in order to have a physical interpretation, some constraints should be incorporated in the signal or image processing technique, such as the non-negativity of the solution. This paper deals with the non-negative pre-image problem in kernel machines, for nonlinear pattern recognition. While kernel machines operate in a feature space, associated to the used kernel function, a pre-image technique is often required to map back features into the input space. We derive a gradient-based algorithm to solve the pre-image problem, and to guarantee the non-negativity of the solution. Its convergence speed is significantly improved due to a weighted stepsize approach. The relevance of the proposed method is demonstrated with experiments on real datasets, where only a couple of iterations are necessary.
Mots clés
machine learning
pre-image problem
non-negativity
convergence
gradient methods
image recognition
learning (artificial intelligence)
physical interpretation
signal processing technique
image processing technique
kernel machines
nonnegative pre-image problem
feature space
nonlinear pattern recognition
gradient-based algorithm
convergence speed
weighted stepsize approach
real datasets
Kernel
Pattern recognition
Principal component analysis
Noise reduction
Linear programming
Signal processing
Optimization
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
Loading...