Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
We introduce a boosting framework to solve a classification problem with added manifold and ambient regularization costs. It allows for a natural extension of boosting into both s...
Nicolas Loeff, David A. Forsyth, Deepak Ramachandr...
The k-Nearest Neighbors algorithm can be easily adapted to classify complex objects (e.g. sets, graphs) as long as a proper dissimilarity function is given over an input space. Bo...
Adam Woznica, Alexandros Kalousis, Melanie Hilario
The use of Mercer kernel methods in statistical learning theory provides for strong learning capabilities, as seen in kernel principal component analysis and support vector machin...
Rademacher and Gaussian complexities are successfully used in learning theory for measuring the capacity of the class of functions to be learned. One of the most important propert...