Sciweavers

18 search results - page 1 / 4
» A Novel Neural Topic Model and Its Supervised Extension
Sort
View
TNN
2010
234views Management» more  TNN 2010»
12 years 11 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
ICDM
2009
IEEE
98views Data Mining» more  ICDM 2009»
13 years 11 months ago
Topic Distributions over Links on Web
—It is well known that Web users create links with different intentions. However, a key question, which is not well studied, is how to categorize the links and how to quantify th...
Jie Tang, Jing Zhang, Jeffrey Xu Yu, Zi Yang, Keke...
IJCNN
2006
IEEE
13 years 11 months ago
TempUnit: A bio-inspired neural network model for signal processing
– We have developed and tested a novel artificial neural network for the processing of temporal signals. The working of the units (TempUnit) is based on the mechanism of temporal...
Olivier F. Manette, Marc A. Maier
CVPR
2010
IEEE
14 years 1 months ago
Supervised Translation-Invariant Sparse Coding
In this paper, we propose a novel supervised hierarchical sparse coding model based on local image descriptors for classification tasks. The supervised dictionary training is perf...
Jianchao Yang, Kai Yu, Thomas Huang
IJCNN
2007
IEEE
13 years 11 months ago
Risk Assessment Algorithms Based on Recursive Neural Networks
— The assessment of highly-risky situations at road intersections have been recently revealed as an important research topic within the context of the automotive industry. In thi...
Alejandro Chinea Manrique De Lara, Michel Parent