Table 12. Training loss(T_loss), training accuracy (T_acc), validation loss (V_loss), validation accuracy (V_acc), test loss (Te_loss), test accuracy (Te_acc) for each of the optimizers corresponding to the learning rates.
OP | LR | T_Acc | V_Loss | V_Acc | Te_Loss | Te_Acc | Findings |
---|---|---|---|---|---|---|---|
Adam | 0.001 | 99.66 | 0.021 | 99.49 | 0.056 | 98.74 | Highest accuracy |
0.0001 | 99.35 | 0.035 | 99.20 | 0.061 | 98.14 | Less accuracy | |
Nadam | 0.001 | 99.51 | 0.031 | 99.29 | 0.057 | 98.32 | Less accuracy |
0.0001 | 99.31 | 0.368 | 98.92 | 0.068 | 97.89 | Less accuracy | |
Adamax | 0.001 | 99.06 | 0.041 | 98.73 | 0.073 | 97.65 | Less accuracy |
0.0001 | 98.99 | 0.066 | 98.57 | 0.081 | 97.42 | Less accuracy |