The radial basis function (RBF) network has its foundation in the conventional approximation
theory. It has the capability of universal approximation. The RBF network is a popular …

Conventional model-based data processing methods are computationally expensive and
require experts' knowledge for the modelling of a system. Neural networks are a model-free …

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 …

The RBFN is a universal approximator, with a solid foundation in the conventional
approximation theory. The RBFN is a popular alternative to the MLP, since it has a simpler …

Although computational intelligence (CI) covers a vast variety of different methods it still
lacks an integrative theory. Several proposals for CI foundations are discussed: computing …

W pracy przedstawiono przegląd ontogenicznych modeli sieci neuronowych, czyli takich
modeli, które dopasowują swoją strukturę (liczbę neuronów i połączeń pomiędzy nimi) do …

Neural networks use neurons of the same type in each layer but such architecture cannot
lead to data models of optimal complexity and accuracy. Networks with architectures …

In this paper, we present the application of a neural network for events classification in a
high-energy physics experiment. As a network model we use a multi-layer perceptron with a …

Computationally efficient sequential learning algorithms are developed for direct-link
resource-allocating networks (DRANs). These are achieved by decomposing existing …

Novel fast and efficient sequential learning algorithms are proposed for direct-link radial
basis function (DRBF) networks. The dynamic DRBF network is trained using the recently …