: This paper describes a possibility of expressing ordering constraints among non-sister constituents in binary branching syntactic structures on a local basis, supported by viewin...
We propose a direct reconstruction algorithm for Computed Tomography, based on a local fusion of a few preliminary image estimates by means of a non-linear fusion rule. One such ru...
We propose an algorithm for function approximation that evolves a set of hierarchical piece-wise linear regressors. The algorithm, named HIRE-Lin, follows the iterative rule learn...
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all ...
In this paper we show that efficient object recognition can be obtained by combining informative features with linear classification. The results demonstrate the superiority of in...