10054 search results - page 5 / 2011 » On the Complexity of Function Learning |
STOC
1993
ACM
14 years 1 months ago
1993
ACM
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...
ICML
2008
IEEE
14 years 10 months ago
2008
IEEE
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...
ICML
2007
IEEE
14 years 10 months ago
2007
IEEE
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...
ICCV
2009
IEEE
13 years 7 months ago
2009
IEEE
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...
ALT
2004
Springer
14 years 6 months ago
2004
Springer
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...