JMLR
2008
13 years 11 months ago
2008
We study a generative model in which hidden causes combine competitively to produce observations. Multiple active causes combine to determine the value of an observed variable thr...
PR
2007
13 years 11 months ago
2007
In this paper, we propose a new constructive method, based on cooperative coevolution, for designing automatically the structure of a neural network for classification. Our appro...
PR
2007
13 years 11 months ago
2007
The eigenvalues of the Dirichlet Laplacian are used to generate three different sets of features for shape recognition and classification in binary images. The generated feature...
NN
2007
Springer
13 years 11 months ago
2007
Springer
Real world processes with an “intensity” and “direction” component can be made complex by convenience of representation (vector fields, radar, sonar), and their processin...
NN
2007
Springer
13 years 11 months ago
2007
Springer
Simultaneous recordings from populations of neurons in the inferior temporal visual cortex show that most of the information about which stimulus was shown is available in the num...
NN
2007
Springer
13 years 11 months ago
2007
Springer
NN
2007
Springer
13 years 11 months ago
2007
Springer
In the last decade, recurrent neural networks (RNNs) have attracted more efforts in inferring genetic regulatory networks (GRNs), using time series gene expression data from micro...
NN
2007
Springer
13 years 11 months ago
2007
Springer
An enhanced self-organizing incremental neural network (ESOINN) is proposed to accomplish online unsupervised learning tasks. It improves the self-organizing incremental neural ne...
NN
2007
Springer
13 years 11 months ago
2007
Springer
NN
2007
Springer
13 years 11 months ago
2007
Springer
