78 search results - page 4 / 16 » Influence of weight-decay training in input selection method... |
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
We present a speech pre-processing scheme (SPPS) for robust speech recognition in the moving motorcycle environment. The SPPS is dynamically adapted during the run-time operation ...
NPL
1998
14 years 9 months ago
1998
A new architecture and method for feature selection and extraction of logical rules from neural networks trained with backpropagation algorithm is presented. The network consists ...
83
Voted
NIPS
2007
14 years 11 months ago
2007
A situation where training and test samples follow different input distributions is called covariate shift. Under covariate shift, standard learning methods such as maximum likeli...
ICCV
2003
IEEE
15 years 11 months ago
2003
IEEE
Visual learning is expected to be a continuous and robust process, which treats input images and pixels selectively. In this paper we present a method for subspace learning, which...
FSKD
2005
Springer
15 years 3 months ago
2005
Springer
Abstract. In the artificial neural networks (ANNs), feature selection is a wellresearched problem, which can improve the network performance and speed up the training of the networ...