17 search results - page 1 / 4 » Invariance of MLP Training to Input Feature De-correlation |
FLAIRS
2004
13 years 6 months ago
2004
In the neural network literature, input feature de-correlation is often referred as one pre-processing technique used to improve the MLP training speed. However, in this paper, we...
ICASSP
2009
IEEE
13 years 11 months ago
2009
IEEE
Features derived from Multi-Layer Perceptrons (MLPs) are becoming increasingly popular for speech recognition. This paper describes various schemes for applying these features to ...
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
This paper introduces the sparse multilayer perceptron (SMLP) which learns the transformation from the inputs to the targets as in multilayer perceptron (MLP) while the outputs of...
ESANN
2004
13 years 6 months ago
2004
The classification problem of determining if a surveillance camera sees persons is tackled with two neural models: the Self-Organizing Map (SOM) with supervision as in a classical ...
NPL
1998
13 years 4 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 ...