Conference Papers in Science

Conference Paper

Using Feed Forward Neural Network to Solve Eigenvalue Problems

Table 8

Weight and bias of the network for different training algorithms.
(a)
Weights and bias for trainlm
Net.IW Net.LW Net.B{1}
0.54590.78960.4897
0.94320.79920.9729
0.32150.04960.7485
0.80650.28320.5678
0.60140.65350.2990
(b)
Weights and bias for trainbfg
Net.IW Net.LW Net.B{1}
0.88590.47370.8309
0.21380.95120.8246
0.03460.24900.4530
0.45110.38640.3806
0.01380.43140.9259
(c)
Weights and bias for trainbr
Net.IW Net.LW Net.B{1}
0.31820.17560.9988
0.89930.50730.3745
0.00700.29380.5081
0.17390.87330.7485
0.76770.82350.3999