Sciweavers

762 search results - page 50 / 153
» Constructive Neural Network Learning Algorithms
Sort
View
ECML
2007
Springer
15 years 8 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
IPPS
1998
IEEE
15 years 6 months ago
Artificial Neural Networks on Reconfigurable Meshes
:Artificial neural networks(ANN) have been used successfully in applications such as pattern recognition, image processing, automation and control. Majority of today's applica...
Jing-Fu Fu Jenq, Wing Ning Li
IJCNN
2000
IEEE
15 years 6 months ago
Supervised Scaled Regression Clustering: An Alternative to Neural Networks
: This paper describes a rather novel method for the supervised training of regression systems that can be an alternative to feedforward Artificial Neural Networks (ANNs) trained w...
Mark J. Embrechts, Dirk Devogelaere, Marcel Rijcka...
AI
2009
Springer
15 years 9 months ago
Grid-Enabled Adaptive Metamodeling and Active Learning for Computer Based Design
Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a feasible alte...
Dirk Gorissen
KDD
2002
ACM
157views Data Mining» more  KDD 2002»
16 years 2 months ago
Exploiting unlabeled data in ensemble methods
An adaptive semi-supervised ensemble method, ASSEMBLE, is proposed that constructs classification ensembles based on both labeled and unlabeled data. ASSEMBLE alternates between a...
Kristin P. Bennett, Ayhan Demiriz, Richard Maclin