Free-knot Splines Approximation of s-monotone Functions |
| |
Authors: | VN Konovalov D Leviatan |
| |
Institution: | (1) Institute of Mathematics, National Academy of Sciences of Ukraine, Kyiv, 01601, Ukraine;(2) School of Mathematical Sciences, Tel Aviv University, Tel Aviv, 69978, Israel |
| |
Abstract: | Let I be a finite interval and r,sN. Given a set M, of functions defined on I, denote by
+
s
M the subset of all functions yM such that the s-difference
s
y() is nonnegative on I, >0. Further, denote by
+
s
W
p
r
, the class of functions x on I with the seminorm x
(r)L
p
1, such that
s
x0, >0. Let M
n
(h
k
):={
i=1
n
c
i
h
k
(w
i
t–
i
)c
i
,w
i
,
i
R, be a single hidden layer perceptron univariate model with n units in the hidden layer, and activation functions h
k
(t)=t
+
k
, tR, kN
0. We give two-sided estimates both of the best unconstrained approximation E(
+
s
W
p
r
,M
n
(h
k
))L
q
, k=r–1,r, s=0,1,...,r+1, and of the best s-monotonicity preserving approximation E(
+
s
W
p
r
,
+
s
M
n
(h
k
))L
q
, k=r–1,r, s=0,1,...,r+1. The most significant results are contained in theorem 2.2. |
| |
Keywords: | shape preserving relative width free-knot spline order of approximation single hidden layer perceptron model |
本文献已被 SpringerLink 等数据库收录! |
|