Tomographic Considerations in Ensemble Bias/Variance Decomposition
Classifier decision fusion has been shown to act in a manner analogous to the back-projection of Radon transformations when individual classifier feature sets are non or partially overlapping. It is possible, via this analogy, to demonstrate that standard linear classifier fusion introduces a morphological bias into the decision space due to the implicit angular undersampling of the feature selection process. In standard image-based (eg medical) tomography, removal of this bias involves a filtration process, and an analogous n-dimensional processes can be shown to exist for decision fusion using Hogbom deconvolution. Countering the biasing process implicit in linear fusion, however, is the fact that back projection of Radon transformation (being additive) should act to reduce variance within the composite decision space. In principle, this additive variance-reduction should still apply to tomographicallyfiltered back-projection, unless the filtration process contravenes. We therefore argue that when feature selection is carried-out independently for each classifier (as in e.g. multi-modal problems) unfiltered decision fusion, while in general being variance-decreasing, is typically also bias-increasing. By employing a shot noise model, we seek to quantify how far filtration acts to rectify this problem, such that feature selection can be made both bias and variance reducing within an ensemble fusion context.