Generative Modeling on MNIST dynamically binarized (train)
-97.21Training ELBORODEO
Evaluation results
| Method | Links | |
|---|---|---|
| RODEONumber of layers=Three layers2022.02 | -97.21 | |
| Double CVNumber of layers=Three layers2022.02 | -97.59 | |
| DisARMNumber of layers=Three layers2022.02 | -97.95 | |
| RODEONumber of layers=Four layers2022.02 | -98.67 | |
| Double CVNumber of layers=Four layers2022.02 | -98.73 | |
| DisARMNumber of layers=Four layers2022.02 | -98.97 | |
| RODEONumber of layers=Two layers2022.02 | -103.15 | |
| DisARMNumber of layers=Two layers2022.02 | -103.39 | |
| Double CVNumber of layers=Two layers2022.02 | -103.52 |