Sciweavers

1032 search results - page 151 / 207
» Efficient Learning of Neural Networks with Evolutionary Algo...
Sort
View
ESANN
2003
14 years 11 months ago
On the weight dynamics of recurrent learning
We derive continuous-time batch and online versions of the recently introduced efficient O(N2 ) training algorithm of Atiya and Parlos [2000] for fully recurrent networks. A mathem...
Ulf D. Schiller, Jochen J. Steil
NECO
2008
170views more  NECO 2008»
14 years 9 months ago
Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
Deep Belief Networks (DBN) are generative neural network models with many layers of hidden explanatory factors, recently introduced by Hinton et al., along with a greedy layer-wis...
Nicolas Le Roux, Yoshua Bengio
ICANN
2005
Springer
15 years 3 months ago
Reducing the Effect of Out-Voting Problem in Ensemble Based Incremental Support Vector Machines
Although Support Vector Machines (SVMs) have been successfully applied to solve a large number of classification and regression problems, they suffer from the catastrophic forgetti...
Zeki Erdem, Robi Polikar, Fikret S. Gürgen, N...
IJKESDP
2010
94views more  IJKESDP 2010»
14 years 4 months ago
Neuro-fuzzy-combiner: an effective multiple classifier system
: A neuro-fuzzy-combiner (NFC) is proposed to design an efficient multiple classifier system (MCS) with an aim to have an effective solution scheme for difficult classification pro...
Ashish Ghosh, B. Uma Shankar, Lorenzo Bruzzone, Sa...
ICC
2007
IEEE
120views Communications» more  ICC 2007»
15 years 4 months ago
Dynamic Network Selection using Kernels
—We present a new algorithm for vertical handover and dynamic network selection, based on a combination of multiattribute utility theory, kernel learning and stochastic gradient ...
Eric van den Berg, Praveen Gopalakrishnan, Byungsu...