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} |
| 0.5459 | 0.7896 | 0.4897 | 0.9432 | 0.7992 | 0.9729 | 0.3215 | 0.0496 | 0.7485 | 0.8065 | 0.2832 | 0.5678 | 0.6014 | 0.6535 | 0.2990 |
|
|
(b) |
| Weights and bias for trainbfg | Net.IW | Net.LW | Net.B{1} |
| 0.8859 | 0.4737 | 0.8309 | 0.2138 | 0.9512 | 0.8246 | 0.0346 | 0.2490 | 0.4530 | 0.4511 | 0.3864 | 0.3806 | 0.0138 | 0.4314 | 0.9259 |
|
|
(c) |
| Weights and bias for trainbr | Net.IW | Net.LW | Net.B{1} |
| 0.3182 | 0.1756 | 0.9988 | 0.8993 | 0.5073 | 0.3745 | 0.0070 | 0.2938 | 0.5081 | 0.1739 | 0.8733 | 0.7485 | 0.7677 | 0.8235 | 0.3999 |
|
|