Biomedical Engineering Reference
In-Depth Information
(a)
Ladder Network Technique
1
0.99
0.98
0.97
0.96
0.95
0.94
0.93
0.92
0.91
0
5
10
15
20
25
30
35
No. of Nodes
(b)
1
data1
0.99
0.98
0.97
0.96
0.95
0.94
0.93
0.92
0.91
0
5
10
15
20
25
30
35
Number of nodes
Fig. 6
a Ladder iterative voltage magnitude. b BPN voltage magnitudes after training
The steps of the well-established training algorithm based upon Network's
steepest descent technique is as given below:
1. Read the training set and randomly initialize the weights. Set iteration index
n = 1.
2. Set training set index p = 1.
3. Propagate X
P
through the network.
4. Determine the error vector of the pth training set,
E
p
¼
O
p
Y
p
where O
p
is the vector of expected output.
Search WWH ::
Custom Search