Information Technology Reference
In-Depth Information
0.6
0.4
0.2
0
−0.2
−0.4
−0.6
−0.8
−10
−8
−6
−4
−2
0
2
4
6
8
10
iterations
Fig. 12.9
Approximation of the test function of Eq. (
12.24
)(
dashed line
), using a one hidden layer
FNN with sigmoidal basis functions
0.6
0.4
0.2
0
−0.2
−0.4
−0.6
−0.8
−10
−8
−6
−4
−2
0
2
4
6
8
10
x
Fig. 12.10
Approximation of the test function of Eq. (
12.24
)(
dashed line
), using an RBF neural
network with Gaussian basis functions
f.x/D
2:186x 12:864; 10x<2
4:246x; 2x<0
10e
.0:05xC0:5/
sinŒ.0:001x C 0:05/x; 0x10
(12.24)
3. Test function 3 given in Eq. (
12.25
) over the domain D D Œ10;10: