Image Classification on MNIST (test) (Accuracy, Steps, and Timing)
98.1AccuracyAdam
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| AdamArchitecture=1 x 128, Steps (k)=1.6 ± 0.5, Time (s)=4.7 ± 1.4, Time/Step (ms)=2.95 ± 0.012025.06 | 98.1 | — | — | — | |
| AdamArchitecture=4 x 128, Steps (k)=1.8 ± 0.7, Time (s)=5.7 ± 2.3, Time/Step (ms)=3.09 ± 0.052025.06 | 98.1 | — | — | — | |
| AdamArchitecture=4 x 128 + Skip, Steps (k)=1.4 ± 0.5, Time (s)=4.3 ± 1.6, Time/Step (ms)=3.08 ± 0.012025.06 | 98.1 | — | — | — | |
| AdamArchitecture=4 x 16 + Skip2025.06 | 97.9 | 4 | 13.7 | 3.4 | |
| FAArchitecture=1 x 128, Steps (k)=8.0 ± 1.1, Time (s)=23.3 ± 3.1, Time/Step (ms)=2.92 ± 0.022025.06 | 97.6 | — | — | — | |
| AdamArchitecture=4 x 162025.06 | 97.4 | 5.4 | 18.4 | 3.41 | |
| SGDArchitecture=4 x 128, Steps (k)=32.4 ± 2.3, Time (s)=96.2 ± 7.2, Time/Step (ms)=2.97 ± 0.032025.06 | 96.9 | — | — | — | |
| SGDArchitecture=1 x 128, Steps (k)=58.6 ± 7.2, Time (s)=171.4 ± 21.4, Time/Step (ms)=2.92 ± 0.012025.06 | 96.8 | — | — | — | |
| SGDArchitecture=4 x 16 + Skip2025.06 | 96.7 | 51.4 | 166.7 | 3.25 | |
| SGDArchitecture=4 x 128 + Skip, Steps (k)=28.2 ± 7.2, Time (s)=84.9 ± 21.9, Time/Step (ms)=3.01 ± 0.012025.06 | 96.6 | — | — | — | |
| DTSemNetTree Height=82026.05 | 96.1 | — | 306 | — | |
| SGDArchitecture=4 x 162025.06 | 96 | 50.4 | 161 | 3.2 | |
| DRArchitecture=1 x 128, Steps (k)=16.6 ± 3.3, Time (s)=3.7 ± 0.7, Time/Step (ms)=0.22 ± 0.002025.06 | 95.8 | — | — | — | |
| FF (Adam)Architecture=1 x 128, Steps (k)=82.4 ± 11.8, Time (s)=256.2 ± 35.2, Time/Step (ms)=3.12 ± 0.042025.06 | 95.6 | — | — | — | |
| FAArchitecture=4 x 128, Steps (k)=20.0 ± 6.2, Time (s)=60.2 ± 18.3, Time/Step (ms)=3.02 ± 0.032025.06 | 95.4 | — | — | — | |
| TAOTree Height=82026.05 | 95 | — | 1,200 | — | |
| DRArchitecture=4 x 128 + Skip, Steps (k)=21.8 ± 6.0, Time (s)=9.3 ± 2.6, Time/Step (ms)=0.43 ± 0.002025.06 | 94.9 | — | — | — | |
| FF (Adam)Architecture=4 x 128, Steps (k)=66.0 ± 9.3, Time (s)=220.3 ± 32.1, Time/Step (ms)=3.35 ± 0.062025.06 | 94.3 | — | — | — | |
| DGTTree Height=82026.05 | 94 | — | 288 | — | |
| CPArchitecture=1 x 128, Steps (k)=41.6 ± 11.4, Time (s)=8.6 ± 2.3, Time/Step (ms)=0.21 ± 0.002025.06 | 92.4 | — | — | — | |
| APArchitecture=1 x 128, Steps (k)=25.8 ± 5.4, Time (s)=2.3 ± 0.5, Time/Step (ms)=0.09 ± 0.002025.06 | 91.5 | — | — | — | |
| CPArchitecture=4 x 128 + Skip, Steps (k)=34.2 ± 3.5, Time (s)=18.7 ± 1.9, Time/Step (ms)=0.55 ± 0.002025.06 | 91.1 | — | — | — | |
| APArchitecture=4 x 128 + Skip, Steps (k)=32.6 ± 9.3, Time (s)=6.9 ± 2.0, Time/Step (ms)=0.21 ± 0.002025.06 | 90.3 | — | — | — | |
| FF (Adam)Architecture=4 x 162025.06 | 88.3 | 29 | 108.3 | 3.73 | |
| DRArchitecture=4 x 128, Steps (k)=29.6 ± 7.3, Time (s)=10.6 ± 2.6, Time/Step (ms)=0.36 ± 0.002025.06 | 85.5 | — | — | — | |
| CPArchitecture=4 x 128, Steps (k)=47.8 ± 9.5, Time (s)=17.1 ± 3.5, Time/Step (ms)=0.36 ± 0.002025.06 | 79.9 | — | — | — | |
| APArchitecture=4 x 128, Steps (k)=46.2 ± 4.2, Time (s)=9.4 ± 0.8, Time/Step (ms)=0.20 ± 0.002025.06 | 79.6 | — | — | — | |
| AdamArchitecture=1 x 322025.06 | 77.8 | 26.2 | 81.7 | 3.11 | |
| SGDArchitecture=1 x 322025.06 | 71.7 | 133 | 402.8 | 3.03 | |
| DRArchitecture=4 x 16 + Skip2025.06 | 71.3 | 16 | 1,303.8 | 81.47 | |
| FF (Adam)Architecture=1 x 322025.06 | 70.6 | 19.6 | 65.1 | 3.35 | |
| CPArchitecture=4 x 16 + Skip2025.06 | 69.6 | 44.2 | 1,609.5 | 36.42 | |
| APArchitecture=4 x 16 + Skip2025.06 | 69.4 | 46.2 | 3,240.5 | 70.14 | |
| CRO-DTTree Height=82026.05 | 58.2 | — | 4,659 | — | |
| DRArchitecture=4 x 162025.06 | 55.4 | 99.4 | 7,713.7 | 77.6 | |
| DRArchitecture=1 x 322025.06 | 51.7 | 12.4 | 31.7 | 2.55 | |
| CPArchitecture=1 x 322025.06 | 49.9 | 25.6 | 72.1 | 2.82 | |
| APArchitecture=1 x 322025.06 | 49.8 | 25.8 | 72.2 | 2.8 | |
| APArchitecture=4 x 162025.06 | 46.4 | 20.8 | 1,358.7 | 65.32 | |
| CPArchitecture=4 x 162025.06 | 46.4 | 20.6 | 1,426.7 | 69.24 | |
| FF (SGD)Architecture=1 x 322025.06 | 24.5 | 4 | 13.3 | 3.32 | |
| FF (SGD)Architecture=4 x 162025.06 | 20 | 2.2 | 8.1 | 3.58 | |
| FF (SGD)Architecture=1 x 128, Steps (k)=1.6 ± 1.7, Time (s)=5.1 ± 5.6, Time/Step (ms)=3.12 ± 0.082025.06 | 12.7 | — | — | — | |
| FF (SGD)Architecture=4 x 128, Steps (k)=2.8 ± 1.7, Time (s)=9.0 ± 5.4, Time/Step (ms)=3.24 ± 0.052025.06 | 11.9 | — | — | — |