3718 search results - page 286 / 744 » On learning with dissimilarity functions |
193
click to vote
ESANN
2006
15 years 8 months ago
2006
Neural gas (NG) constitutes a very robust clustering algorithm which can be derived as stochastic gradient descent from a cost function closely connected to the quantization error...
175
click to vote
ICML
2003
IEEE
16 years 7 months ago
2003
IEEE
When the goal is to achieve the best correct classification rate, cross entropy and mean squared error are typical cost functions used to optimize classifier performance. However,...
241
click to vote
EUROCOLT
1999
Springer
15 years 11 months ago
1999
Springer
We consider algorithms for combining advice from a set of experts. In each trial, the algorithm receives the predictions of the experts and produces its own prediction. A loss func...
180
click to vote
IANDC
2006
15 years 6 months ago
2006
This paper studies the complexity of learning classes of expressions in propositional logic from equivalence queries and membership queries. In particular, we focus on bounding th...
204
click to vote
ECML
2005
Springer
16 years 6 days ago
2005
Springer
This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing Amari...