The choice of transfer functions may strongly influence complexity and performance of
neural networks used in classification and approximation tasks. A taxonomy of activation …

The choice of transfer functions may strongly influence complexity and performance of
neural networks. Although sigmoidal transfer functions are the most common there is no a …

Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast
learning of neural networks. Families of parameterized transfer functions provide flexible …

The choice of activation functions may strongly influence complexity and performance of
neural networks. However a limited number of activation functions have been used in …

Sets of multivariable functions that can be approximated with" dimension-independent" rates
either by linear approximators or by neural networks having various types of computational …

Mapping capabilities of a three-layer feedforward neural network with a finite number of
hidden units which have sigmoid functions as their nonlinearities are discussed. It is proved …

In this article we propose a new class of artificial neural networks for classification and
function approximation. These networks are referred to as shunting inhibitory artificial neural …

As hardware implementations of backpropagation and related training algorithms are
anticipated, the choice of a sigmoidal function should be carefully justified. Attention should …

The spectra for many common artificial neural network activation functions are derived,
including members of the sigmoid family, the Gaussian function, rectangular pulses and …

An innovative neural-based approach for function approximation is proposed by means of
the spectral analysis of the function y (x) to be approximated. Approximation is obtained by …