Sciweavers

220 search results - page 14 / 44
» An improvement on learning with local and global consistency
Sort
View
NN
2000
Springer
123views Neural Networks» more  NN 2000»
13 years 7 months ago
Local minima and plateaus in hierarchical structures of multilayer perceptrons
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
Kenji Fukumizu, Shun-ichi Amari
IROS
2007
IEEE
119views Robotics» more  IROS 2007»
14 years 2 months ago
Scalable SLAM building conditionally independent local maps
— Local maps algorithms have demonstrated to be well suited for mapping large environments as can reduce the computational cost and improve the consistency of the final estimati...
Pedro Pinies, Juan D. Tardós
ICNC
2005
Springer
14 years 1 months ago
A Game-Theoretic Approach to Competitive Learning in Self-Organizing Maps
Abstract. Self-Organizing Maps (SOM) is a powerful tool for clustering and discovering patterns in data. Competitive learning in the SOM training process focusses on finding a neu...
Joseph P. Herbert, Jingtao Yao
ECML
2007
Springer
14 years 2 months ago
Nondeterministic Discretization of Weights Improves Accuracy of Neural Networks
Abstract. The paper investigates modification of backpropagation algorithm, consisting of discretization of neural network weights after each training cycle. This modification, a...
Marcin Wojnarski
WSC
2007
13 years 10 months ago
Simulation results and formalism for global-local scheduling in semiconductor manufacturing facilities
This article deals with an approach for managing scheduling in semiconductor manufacturing facilities. The proposed approach ensures consistency between global and local schedulin...
Mickaël Bureau, Stéphane Dauzèr...