DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación
Contribución de congreso (ConferenceOutput)
Deterministic Feature Decoupling by Surfing Invariance Manifolds
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 4-8 May 2020 . -- 5 pags., 1 fig., We introduce a formalism that justifies and extends a heuristic method for algebraically decoupling deterministic features that recently proved useful for improving feature-based classification. Our new formalism is based on defining transformations inside manifolds, by following trajectories along the features' gradients. Through these transformations we define a normalization that, we demonstrate, allows for decoupling differentiable features. By applying this to sampling moments, we obtain a quasi-analytic solution for the orthokurtosis, a modification of the kurtosis that is not just decoupled from mean and variance, but also from skewness. After theoretically motivating feature decoupling for random data distributions, we illustrate with a regression problem example how decoupled features may perform significantly better than coupled ones., Funded by the Spanish Government grant FIS2016-75891-P