224 search results - page 28 / 45 » Bounding Learning Time in XCS |
ICML
2010
IEEE
13 years 9 months ago
2010
IEEE
When equipped with kernel functions, online learning algorithms are susceptible to the "curse of kernelization" that causes unbounded growth in the model size. To addres...
COLT
1999
Springer
14 years 22 days ago
1999
Springer
We propose a new boosting algorithm. This boosting algorithm is an adaptive version of the boost by majority algorithm and combines bounded goals of the boost by majority algorith...
ALT
2005
Springer
14 years 5 months ago
2005
Springer
This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedba...
NCA
2007
IEEE
14 years 2 months ago
2007
IEEE
Developing middleware services for dynamic distributed systems, e.g., ad-hoc networks, is a challenging task given that such services deal with dynamically changing membership and...
COLT
2008
Springer
13 years 10 months ago
2008
Springer
We define a model of learning probabilistic acyclic circuits using value injection queries, in which an arbitrary subset of wires is set to fixed values, and the value on the sing...