Update README.md
Browse files
README.md
CHANGED
|
@@ -13,4 +13,4 @@ A super tiny mnist model to demostrate the potential of the learnable activation
|
|
| 13 |
The model can reach 96.6% accuracy with only a 1.3k parameter-size.
|
| 14 |
|
| 15 |
The OptAEG-V1 learnable activation is based on a theory of Arithmetic Expression Geometry which is still in developing.
|
| 16 |
-
Please visit https://github.com/mountain/aeg-paper for a reference
|
|
|
|
| 13 |
The model can reach 96.6% accuracy with only a 1.3k parameter-size.
|
| 14 |
|
| 15 |
The OptAEG-V1 learnable activation is based on a theory of Arithmetic Expression Geometry which is still in developing.
|
| 16 |
+
Please visit the draft papers on [theory](https://github.com/mountain/aeg-paper) and [neurual networks](https://github.com/mountain/optim-aeg) for a reference
|