2327 search results - page 80 / 466 » Consistency of functional learning methods based on derivati... |
139
click to vote
IJCNN
2008
IEEE
16 years 21 days ago
2008
IEEE
— In this paper we address the reliability of policies derived by Reinforcement Learning on a limited amount of observations. This can be done in a principled manner by taking in...
163
click to vote
DEXAW
2008
IEEE
16 years 23 days ago
2008
IEEE
—The ontology learning from text cycle consists of the consecutive phases of term, synonym, concept, taxonomy and relation extraction. In this paper, a proposal towards the unsup...
169
click to vote
JEI
2006
15 years 6 months ago
2006
The method of paired comparison based on Thurstone's Case V of his Law of Comparative Judgments is often used as a psychophysical method to derive interval scales of perceptua...
178
click to vote
ICANN
2003
Springer
15 years 11 months ago
2003
Springer
Model based learning systems usually face to a problem of forgetting as a result of the incremental learning of new instances. Normally, the systems have to re-learn past instances...
194
click to vote
NIPS
2008
15 years 7 months ago
2008
Actor-critic algorithms for reinforcement learning are achieving renewed popularity due to their good convergence properties in situations where other approaches often fail (e.g.,...