ann_burst_cycle
done · peak unseen_mismatch 96.8
Referenced by
α schedule
α 3.0 ×150 α 1.0 ×150 α 2.1429 ×150 α 1.0 ×150 α 1.2857 ×150 α 1.0 ×150 α 1.4 ×150 α 1.0 ×150 α 1.4 ×150 α 1.0 ×150 α 1.4 ×150 α 1.0 ×150 α 1.4 ×150 α 1.0 ×150 α 1.4 ×150 α 1.0 ×150
Figures
Results
accuracy by training iteration, mean ± sd over seeds · schedule ends at α = 1.0
seen_* probed at reference α = 1.4 · unseen_* = held-out pairings, uniform (α-independent) · 1000 pairs per condition
| iteration | seen_match | seen_mismatch | unseen_match | unseen_mismatch |
|---|---|---|---|---|
| 150 | 70.1 ± 16.1 | 62.2 ± 12.3 | 67.1 ± 15.6 | 60.3 ± 10.7 |
| 300 | 100.0 ± 0.0 | 40.7 ± 27.0 | 100.0 ± 0.0 | 40.8 ± 27.3 |
| 450 | 99.8 ± 0.3 | 93.8 ± 15.1 | 99.5 ± 0.9 | 93.0 ± 14.8 |
| 600 | 100.0 ± 0.0 | 97.7 ± 3.1 | 100.0 ± 0.0 | 96.8 ± 3.2 |
| 750 | 100.0 ± 0.0 | 97.2 ± 4.1 | 99.7 ± 0.5 | 94.6 ± 5.9 |
| 900 | 100.0 ± 0.0 | 98.1 ± 2.5 | 99.7 ± 0.9 | 94.6 ± 5.6 |
| 1050 | 99.9 ± 0.1 | 97.2 ± 2.4 | 98.7 ± 1.3 | 90.9 ± 6.0 |
| 1200 | 100.0 ± 0.0 | 96.0 ± 3.5 | 99.8 ± 0.4 | 85.9 ± 8.9 |
| 1350 | 99.8 ± 0.3 | 96.2 ± 3.4 | 97.9 ± 1.2 | 84.0 ± 7.6 |
| 1500 | 100.0 ± 0.0 | 93.7 ± 3.5 | 99.8 ± 0.3 | 80.8 ± 10.9 |
| 1650 | 99.8 ± 0.1 | 94.6 ± 3.7 | 96.6 ± 2.1 | 76.2 ± 11.3 |
| 1800 | 100.0 ± 0.0 | 91.3 ± 8.0 | 99.6 ± 0.4 | 75.5 ± 13.8 |
| 1950 | 99.9 ± 0.1 | 95.0 ± 5.2 | 95.3 ± 4.0 | 76.7 ± 12.9 |
| 2100 | 100.0 ± 0.0 | 89.9 ± 10.2 | 98.9 ± 1.9 | 71.6 ± 18.8 |
| 2250 | 99.8 ± 0.3 | 93.6 ± 4.0 | 94.2 ± 3.9 | 70.6 ± 13.3 |
| 2400 | 100.0 ± 0.0 | 85.8 ± 10.5 | 98.5 ± 1.8 | 64.8 ± 14.1 |