Placing spline knots in neural networks using splines as activation functions.

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 ke...

Mô tả đầy đủ

Chi tiết về thư mục
Xuất bản năm:Neurocomputing :an international journal. 17, 3-4 (1997).
Tác giả chính: Hlavácková, Katerina
Định dạng: Bài viết
Ngôn ngữ:English
Những chủ đề: