On Radial Basis Function Net and Kernel Regression: Approximation Ability, Convergence Rate and Receptive Field Size

Radial Basis Function (RBF) network have been studied intensively ([1], [9], [8], [3], [2], [12], [13]). Besides its applications several theoretical results have been obtained. E.g., (1) RBF net can be naturally derived from regularization theory ([9]), (2) RBF net has universal approximation ability [4], (3) RBF net has also best approximation ability ([3],[5]).