4196 search results - page 434 / 840 » Unsupervised Learning of Relations |
173
click to vote
ECML
2005
Springer
16 years 11 days ago
2005
Springer
We present a method for transferring knowledge learned in one task to a related task. Our problem solvers employ reinforcement learning to acquire a model for one task. We then tra...
181
click to vote
ITICSE
2004
ACM
16 years 8 days ago
2004
ACM
The use of generic and generative methods for the development and application of interactive educational software is a relatively unexplored area in industry and education. Advant...
189
click to vote
COLT
2001
Springer
15 years 11 months ago
2001
Springer
We describe a new boosting algorithm which generates only smooth distributions which do not assign too much weight to any single example. We show that this new boosting algorithm ...
186
click to vote
GECCO
2006
Springer
15 years 10 months ago
2006
Springer
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...
195
click to vote
FLAIRS
2007
15 years 9 months ago
2007
Context-sensitive Multiple Task Learning, or csMTL, is presented as a method of inductive transfer that uses a single output neural network and additional contextual inputs for le...