G. BOZZA

We apply here a probabilistic method to predict the effect of quantizing the parameters of a Support Vector Machine. Thank to the particular structure of the SVM, the dependency of the output from the quantization noise can be predicted with good accuracy, and a simple closed–form formula can be derived, without imposing any hard–to–verify assumption

We describe a very fast and automatic formulation of the linear sampling method for three-dimensional electromagnetic inverse scattering problems. This formulation is an extension of a no-sampling implementation recently proposed for two- dimensional configurations. In this 3D framework, regularization occurs independently not only of the...

No description