352 search results - page 18 / 71 » Efficient learning algorithms for changing environments |
126
click to vote
ESANN
2003
15 years 5 months ago
2003
We derive continuous-time batch and online versions of the recently introduced efficient O(N2 ) training algorithm of Atiya and Parlos [2000] for fully recurrent networks. A mathem...
172
click to vote
AIR
2005
15 years 4 months ago
2005
An algorithm has been developed to dynamically schedule heterogeneous tasks on heterogeneous processors in a distributed system. The scheduler operates in an environment with dynam...
121
click to vote
AAAI
2004
15 years 5 months ago
2004
In this paper we report some of the research endeavors we are embarking on as part of the Doctoral research of the first author. We have already completed an investigation of some...
126
click to vote
ICML
2006
IEEE
16 years 4 months ago
2006
IEEE
We formalize the associative bandit problem framework introduced by Kaelbling as a learning-theory problem. The learning environment is modeled as a k-armed bandit where arm payof...
112
click to vote
ICASSP
2008
IEEE
15 years 10 months ago
2008
IEEE
We consider the problem of online learning in a changing environment under sparse user feedback. Specifically, we address the classification of music types according to a user...