Authors : Eman S. Bhaya and Omar A. Al-Sammak
Abstract: If we have a function defined on the real line we cannot approximate this function using a radial bases function neural networks to get an example. It mean we cannot find a radial base forward neural network to approximate a continuous function f. To make this possible we shall put some limits on f. In this study, we shall study approximation of functions in Lp spaces for p>1 defined on the real line using radial base neural network. The weights are fixed in the radial bases functions neural networks to have facilities in practical applications and prove direct theorem using radial basis function neural networks for functions in Lp spaces for p>1.
Eman S. Bhaya and Omar A. Al-Sammak, 2018. Radial Basis Functions Neural Networks Convolution Approximation. Journal of Engineering and Applied Sciences, 13: 8153-8158.