28 search results - page 1 / 6 » Transfer functions: hidden possibilities for better neural n... |
ESANN
2001
13 years 8 months ago
2001
Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
IDEAL
2003
Springer
14 years 5 days ago
2003
Springer
This paper exhaustively discusses and compares the performance differences between radial basis probabilistic neural networks (RBPNN) and radial basis function neural networks (RBF...
IJCNN
2006
IEEE
14 years 1 months ago
2006
IEEE
— This paper applies a recently developed neural network called plausible neural network (PNN) to function approximation. Instead of using error correction, PNN estimates the mut...
IWANN
2005
Springer
14 years 14 days ago
2005
Springer
The generalization ability of different sizes architectures with one and two hidden layers trained with backpropagation combined with early stopping have been analyzed. The depend...
ISCI
2008
13 years 6 months ago
2008
In this paper, two modified constrained learning algorithms are proposed to obtain better generalization performance and faster convergence rate. The additional cost terms of the ...