1393 search results - page 26 / 279 » Machine Learning by Function Decomposition |
COLT
1991
Springer
15 years 3 months ago
1991
Springer
Two extensions of the Linial, Mansour, Nisan AC0 learning algorithm are presented. The LMN method works when input examples are drawn uniformly. The new algorithmsimprove on their...
ICML
2010
IEEE
15 years 26 days ago
2010
IEEE
We introduce new, efficient algorithms for value iteration with multiple reward functions and continuous state. We also give an algorithm for finding the set of all nondominated a...
COLT
1993
Springer
15 years 3 months ago
1993
Springer
We introduce a new formal model in which a learning algorithm must combine a collection of potentially poor but statistically independent hypothesis functions in order to approxima...
ICML
2005
IEEE
16 years 18 days ago
2005
IEEE
This paper presents a search algorithm for finding functions that are highly correlated with an arbitrary set of data. The functions found by the search can be used to approximate...
111
click to vote
ICML
2007
IEEE
16 years 18 days ago
2007
IEEE
We study the problem of learning a classification task in which only a dissimilarity function of the objects is accessible. That is, data are not represented by feature vectors bu...