Table 8 Test results for CNN and HQCNN when paired with the standard SGD, Adam, and Adaptive SGD optimizers
From: Medical image diagnosis based on adaptive Hybrid Quantum CNN
Epochs | Validation Accuracy % SGD Optimizer | Validation Accuracy % Adaptive-SGD Optimizer | Validation Accuracy % Adam Optimizer | |||
|---|---|---|---|---|---|---|
CNN | HQCNN | CNN | HQCNN | CNN | HQCNN | |
1 | 34.54 | 36.37 | 34.87 | 52.64 | 33.13 | 35.23 |
10 | 51.82 | 58.26 | 52.57 | 79.95 | 50.18 | 51.26 |
20 | 62.90 | 70.64 | 62.99 | 91.15 | 54.89 | 55.37 |
30 | 70.05 | 82.77 | 71.30 | 93.77 | 57.47 | 58.73 |
40 | 80.81 | 91.87 | 81.09 | 94.61 | 59.83 | 62.21 |
50 | 88.20 | 93.27 | 88.52 | 95.01 | 61.56 | 63.36 |
60 | 92.09 | 96.48 | 92.35 | 96.69 | 63.01 | 65.29 |
70 | 94.35 | 97.94 | 94.76 | 98.07 | 64.50 | 67.68 |
80 | 95.58 | 97.99 | 96.05 | 98.15 | 65.22 | 67.94 |
90 | 97.88 | 97.69 | 97.90 | 98.20 | 66.40 | 68.01 |
100 | 97.97 | 98.01 | 98.07 | 98.27 | 67.34 | 68.21 |