29 search results - page 3 / 6 » esann 2001 |
ESANN
2001
13 years 6 months ago
2001
: Many researchers are interesting in applying the neural networks methods to financial data. In fact these data are very complex, and classical methods do not always give satisfac...
ESANN
2001
13 years 6 months ago
2001
This paper illustrates how canonical correlation analysis can be used for designing efficient visual operators by learning. The approach is highly task oriented and what constitute...
ESANN
2001
13 years 6 months ago
2001
This paper describes a method of supervised learning based on forward selection branching. This method improves fault tolerance by means of combining information related to general...
ESANN
2001
13 years 6 months ago
2001
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
ESANN
2001
13 years 6 months ago
2001
We investigate the use of an unsupervised artificial neural network to form a sparse representation of the underlying causes in a data set. By using fixed lateral connections that...