Now showing items 1-3 of 3
Similarity-based learning for pattern classification
Several standard neural networks, including counterpropagation networks, predictive ART networks, and radial basis function networks, are based on a combination of clustering (unsupervised learning) and mapping (supervised ...
Function approximation using a sinc neural network
Neural networks for function approximation are the basis of many applications. Such networks often use a sigmoidal activation function (e.g. tanh) or a radial basis function (e.g. gaussian). Networks have also been developed ...
Comparison of function approximation with sigmoid and radial basis function networks
Theoretical and computational results have demonstrated that several types of neural networks have the universal approximation property, i.e., the ability to represent any continuous function to an arbitrary degree of ...