1413 search results - page 61 / 283 » ideas 2007 |
ESANN
2007
15 years 1 months ago
2007
Training recurrent neural networks is hard. Recently it has however been discovered that it is possible to just construct a random recurrent topology, and only train a single linea...
105
click to vote
ESANN
2007
15 years 1 months ago
2007
In a previous work, we developed a quasi-efficient maximum likelihood approach for blindly separating stationary, temporally correlated sources modeled by Markov processes. In this...
EUSFLAT
2007
15 years 1 months ago
2007
In this paper we extend a previous definition of gradual dependence as a special kind of (crisp) association rule, in order to measure not only the existence of a tendency, but i...
EUSFLAT
2007
15 years 1 months ago
2007
AHP (Analytic Hierarchy Process) has been widely used in decision making techniques. However, the results from AHP often lose reliability because the comparison matrix does not al...
HCI
2007
15 years 1 months ago
2007
Within the eEurope2010 initiative “An Information Society for All”, development methods which enable the inclusion of the end-user become essential in order to ensure the parad...