Information Technology Reference
In-Depth Information
8
6
4
2
0
−2
−4
−6
−8
−10
−8
−6
−4
−2
0
2
4
6
8
10
x
Fig. 12.5 Approximation of the test function of Eq. ( 12.23 )( dashed line ), using a feed-forward
neural network with Hermite basis functions
8
6
4
2
0
−2
−4
−6
−8
−10
−8
−6
−4
−2
0
2
4
6
8
10
iterations
Fig. 12.6 Approximation of the test function of Eq. ( 12.23 )( dashed line ), using a one hidden layer
FNN with sigmoidal basis functions
algorithm [ 78 ]. Alternatively, second order (Newton) training methods can be used
[ 118 ].
The following test functions are examined (dashed red lines):
 
Search WWH ::




Custom Search