Table 1 Hyperparameters for regularization.
From: Deep Cytometry: Deep learning with Real-time Inference in Cell Sorting and Flow Cytometry
Trial number (L2 penalty multiplier, dropout keep probability) | ||
|---|---|---|
1 (0.43498, 84.61%) | 2 (0.01698, 83.74%) | 3 (0.00085, 75.27%) |
4 (0.22378, 28.34%) | 5 (0.00771, 38.11%) | 6 (0.06408, 97.57%) |
7 (0.02045, 64.27%) | 8 (0.00294, 66.68%) | 9 (0.02925, 66.28%) |
10 (0.08087, 80.31%) | 11 (0.00011, 98.59%) | 12 (0.00018, 0.23%) |
13 (0.01049, 69.53%) | 14 (0.00726, 58.78%) | 15 (0.00225, 89.91%) |
16 (0.00364, 31.68%) | 17 (0.00139, 55.35%) | 18 (0.06780, 46.09%) |
19 (0.00546, 43.48%) | 20 (0.01878, 53.98%) | 21 (0.00603, 80.00%) |
22 (0.01834, 77.79%) | 23 (0.00476, 73.39%) | 24 (0.00408, 55.14%) |
