905 search results - page 137 / 181 » Active Learning for Pipeline Models |
NN
2000
Springer
13 years 7 months ago
2000
Springer
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
FCSC
2010
13 years 5 months ago
2010
Graphical models have become the basic framework for topic based probabilistic modeling. Especially models with latent variables have proved to be effective in capturing hidden str...
IFIP3
1998
13 years 9 months ago
1998
Development of a wide spread project intended to teaching Computer Science, integrating a considerable number of students all over a country with big geographical extension and sc...
CVIU
2008
13 years 8 months ago
2008
A key problem in video content analysis using dynamic graphical models is to learn a suitable model structure given some observed visual data. We propose a Completed Likelihood AI...
ICANN
2005
Springer
14 years 1 months ago
2005
Springer
Spike synchronisation and de-synchronisation are important for feature binding and separation at various levels in the visual system. We present a model of complex valued neuron ac...