00000cab a22000003a 4500 UP-99796217608822961 Buklod 20231007234818.0 m |o d | ta 090506s xx d | ||r ||||| || DENGII eng Hlavácková, Katerina Placing spline knots in neural networks using splines as activation functions. pp. 159-166 When using feed-forward neural networks with spline activation functions, the quality of approximation depends on the knot placement of spline functions. We demonstrate a method of choosing equidistant knots in each subdivision of the space when an arbitrary initial division is given, in order to keep the approximation error under a predefined limit. Cubic-spline function. Knots of a spline function. Approximation error. Feed-forward neural network. Neurocomputing :an international journal. 17, 3-4 (1997). FO UPD DENG-II Article