12194 search results - page 366 / 2439 » Numberings Optimal for Learning |
175
Voted
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for ...
164
click to vote
ALT
2009
Springer
16 years 3 months ago
2009
Springer
Abstract. A variant of iterative learning in the limit (cf. [LZ96]) is studied when a learner gets negative examples refuting conjectures containing data in excess of the target la...
178
click to vote
FOCI
2007
IEEE
16 years 1 months ago
2007
IEEE
Recent progress in genomics and proteomics makes it possible to understand the biological networks at the systems level. We aim to develop computational models of learning and memo...
155
click to vote
COLT
2005
Springer
16 years 8 days ago
2005
Springer
Abstract. There has been growing interest in practice in using unlabeled data together with labeled data in machine learning, and a number of different approaches have been develo...
163
click to vote
NN
2006
Springer
15 years 6 months ago
2006
Springer
This paper presents an on-line unsupervised learning mechanism for unlabeled data that are polluted by noise. Using a similarity thresholdbased and a local error-based insertion c...