Sciweavers

JMLR
2010
151views more  JMLR 2010»
12 years 11 months ago
Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with e...
Xavier Glorot, Yoshua Bengio
TNN
1998
99views more  TNN 1998»
13 years 4 months ago
Comments on local minima free conditions in multilayer perceptrons
—In this letter we point out that multilayer neural networks (MLP’s) with either sigmoidal units or radial basis functions can be given a canonical form with positive interunit...
Marco Gori, Ah Chung Tsoi
EUROPAR
2005
Springer
13 years 10 months ago
An Approach to Performance Prediction for Parallel Applications
Abstract. Accurately modeling and predicting performance for largescale applications becomes increasingly difficult as system complexity scales dramatically. Analytic predictive mo...
Engin Ipek, Bronis R. de Supinski, Martin Schulz, ...