Integral Transform and Its Application to Neural Network Approximation
Neural networks are widely used to approximate nonlinear functions. In order to study its approximation capability, a theorem of integral representation of functions is developed by using integral transform. Using the developed representation, an approximation order estimation for the bell-shaped neural networks is obtained. The obtained result reveals that the approximation accurately of the bell-shaped neural networks depends not only on the number of hidden neurons, but also on the smoothness of target functions.
KeywordsNeural Network Hide Neuron Sigmoidal Function Target Function Integral Transform
Unable to display preview. Download preview PDF.