Capabilities of radial convolution kernel networks to approximate multivariate functions are investigated. A necessary condition for universal approximation property of convolution kernel networks is given. Kernels that satisfy the condition in arbitrary dimension are investigated in terms of their Hankel and Fourier transforms. A computational example is presented to assess approximation capabilities of different convolution kernel networks.
CITATION STYLE
Coufal, D. (2016). Kernel networks for function approximation. In Communications in Computer and Information Science (Vol. 629, pp. 295–306). Springer Verlag. https://doi.org/10.1007/978-3-319-44188-7_22
Mendeley helps you to discover research relevant for your work.