Image Classification on MNIST permuted (val)
98.6AccuracyYB-Mixer
Evaluation Results
| Method | Links | |
|---|---|---|
| YB-MixerSequence Length (L)=784, Parameters (M)=2.5, Model Dimension=256, Depth=8, Epochs=50, Seed=single2026.06 | 98.6 | |
| TransformerSequence Length (L)=784, Parameters (M)=4.4, Model Dimension=256, Depth=8, Epochs=50, Seed=single2026.06 | 98.3 | |
| S4D-LinSequence Length (L)=784, Parameters (M)=3.2, Model Dimension=256, Depth=8, Epochs=50, Seed=single2026.06 | 98.2 | |
| LRUSequence Length (L)=784, Parameters (M)=2.4, Model Dimension=256, Depth=8, Epochs=50, Seed=single2026.06 | 98 | |
| FNetSequence Length (L)=784, Parameters (M)=2.4, Model Dimension=256, Depth=8, Epochs=50, Seed=single2026.06 | 97.9 |