Table 1:
For hidden layers = 2, input PE = 1, output PE = 1, transfer function = TanhAxon, learning rule = momentum, maximum epochs = 1000, and threshold MSE = 0.01.
Serial no.
Type of ANN
Hidden layer variation H1 H2
Correlation coefficient
MSE
(
sec)
Training
Cross validation
Testing
01
Jordan/Elman network
09
,06
0.782 021 085
0.009 907 153
0.017 699 749
0.013 501 987
7.5
11.3
02
Jordan/Elman network
07,
05
0.775 341 114
0.009 949 377
0.018 167 161
0.013 811 668
7.5
10.8
03
Jordan/Elman network
08,
05
0.777 408 297
0.00 996 472
0.017 879 274
0.013 631 649
10
32.6