12194 search results - page 397 / 2439 » Numberings Optimal for Learning |
156
click to vote
IPTPS
2004
Springer
16 years 4 days ago
2004
Springer
Distributed hash tables have been around for a long time [5, 7]. A number of recent projects propose peerto-peer DHTs, based on multi-hop lookup optimizations. Some of these syste...
196
click to vote
CVPR
1997
IEEE
16 years 8 months ago
1997
IEEE
A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that ar...
182
click to vote
ICML
2004
IEEE
16 years 7 months ago
2004
IEEE
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
176
click to vote
WWW
2005
ACM
16 years 7 months ago
2005
ACM
This paper investigates basic research issues that need to be addressed for developing an architecture that enables repurposing of learning objects in a flexible way. Currently, t...
203
Voted
ICDM
2005
IEEE
16 years 12 days ago
2005
IEEE
Active machine learning algorithms are used when large numbers of unlabeled examples are available and getting labels for them is costly (e.g. requiring consulting a human expert)...