Sciweavers

1443 search results - page 133 / 289
» Learning Generative Models via Discriminative Approaches
Sort
View
85
Voted
BC
2006
105views more  BC 2006»
15 years 21 days ago
A stochastic population approach to the problem of stable recruitment hierarchies in spiking neural networks
Recruitment learning in hierarchies is an inherently unstable process (Valiant, 1994). This paper presents conditions on parameters for a feedforward network to ensure stable recru...
Cengiz Günay, Anthony S. Maida
130
Voted
NN
2010
Springer
225views Neural Networks» more  NN 2010»
14 years 11 months ago
Learning to imitate stochastic time series in a compositional way by chaos
This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
Jun Namikawa, Jun Tani
ECIR
2011
Springer
14 years 4 months ago
Learning Models for Ranking Aggregates
Aggregate ranking tasks are those where documents are not the final ranking outcome, but instead an intermediary component. For instance, in expert search, a ranking of candidate ...
Craig Macdonald, Iadh Ounis
110
Voted
PRL
2006
115views more  PRL 2006»
15 years 17 days ago
A hybrid parallel projection approach to object-based image restoration
Approaches analyzing local characteristics of an image prevail in image restoration. However, they are less effective in cases of restoring images degraded by large size point spr...
Xin Fan, Hua Huang, Dequn Liang, Chun Qi
ICML
2004
IEEE
16 years 1 months ago
Utile distinction hidden Markov models
This paper addresses the problem of constructing good action selection policies for agents acting in partially observable environments, a class of problems generally known as Part...
Daan Wierstra, Marco Wiering