73 search results - page 1 / 15 » Variable projections neural network training |
161
Voted
MCS
2006
Springer
15 years 6 months ago
2006
Springer
8 The training of some types of neural networks leads to separable non-linear least squares problems. These problems may be9 ill-conditioned and require special techniques. A robus...
158
click to vote
CDC
2008
IEEE
16 years 25 days ago
2008
IEEE
— The detection of transient responses, i.e. non– stationarities, that arise in a varying and small fraction of the total number of neural spike trains recorded from chronicall...
212
Voted
IJCNN
2008
IEEE
16 years 23 days ago
2008
IEEE
Abstract— This paper proposes a combination of methodologies based on a recent development –called Extreme Learning Machine (ELM)– decreasing drastically the training time of...
132
Voted
ICANN
2009
Springer
16 years 28 days ago
2009
Springer
Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generati...
183
Voted
IJCNN
2006
IEEE
16 years 11 days ago
2006
IEEE
Abstract— Neural processing of large-scale data sets containing both many input / output variables and a large number of training examples often leads to very large networks. Onc...