1393 search results - page 137 / 279 » Machine Learning by Function Decomposition |
ICML
2008
IEEE
16 years 2 months ago
2008
IEEE
A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. This class...
ALT
2004
Springer
15 years 10 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...
100
click to vote
COLT
1999
Springer
15 years 6 months ago
1999
Springer
We study the problem of PAC-learning Boolean functions with random attribute noise under the uniform distribution. We define a noisy distance measure for function classes and sho...
106
click to vote
LREC
2010
15 years 3 months ago
2010
Automatically translating natural language into machine-readable instructions is one of major interesting and challenging tasks in Natural Language (NL) Processing. This problem c...
104
click to vote
ICML
2005
IEEE
16 years 2 months ago
2005
IEEE
In many domains, a Bayesian network's topological structure is not known a priori and must be inferred from data. This requires a scoring function to measure how well a propo...