Information Technology Reference
In-Depth Information
1.5
1
0.5
0
−0.5
−1
−1.5
10
5
10
5
0
0
−5
−5
y
x
−10
−10
Fig. 12.15
Approximation of the test function of Eq. (
12.26
), using a feed-forward neural network
with Hermite basis functions
1.5
1
0.5
0
−0.5
−1
−1.5
10
5
10
5
0
0
y
−5
−5
x
−10
−10
Fig. 12.16
Approximation of the test function of Eq. (
12.26
), using a one hidden layer FNN with
sigmoidal basis functions
obtained by a one hidden layer FNN with sigmoidal basis functions is shown in
Fig.
12.20
. Finally the approximation achieved by an RBF neural network with
Gaussian activation functions is given in Fig.
12.21
.