28 search results - page 2 / 6 » Transfer functions: hidden possibilities for better neural n... |
KES
1998
Springer
13 years 11 months ago
1998
Springer
Robotic controllers take advantage from neural network learning capabilities as long as the dimensionality of the problem is kept moderate. This paper explores the possibilities of...
ICONIP
2008
13 years 8 months ago
2008
We present a system for regression using MLP neural networks with hyperbolic tangent functions in the input, hidden and output layer. The activation functions in the input and outp...
CONIELECOMP
2006
IEEE
14 years 1 months ago
2006
IEEE
This paper presents a wavelet neural-network for learning and approximation of chaotic time series. Wavelet-networks are inspired by both feed-forward neural networks and the theo...
IJON
2007
13 years 6 months ago
2007
Unlike the conventional neural network theories and implementations, Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden n...
ICANN
2010
Springer
13 years 7 months ago
2010
Springer
Deep autoencoder networks have successfully been applied in unsupervised dimension reduction. The autoencoder has a "bottleneck" middle layer of only a few hidden units, ...