Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,8 @@ It supports **1-channel and 3-channel** 28×28 inputs (e.g., TorchVision MNIST v
|
|
| 31 |
- I appreciate every single contributor to this - direct or indirect - through your invaluable contributions to science that manifested in utilizable AI form.
|
| 32 |
- I have included the training notebook as train_notebook.ipynb - which shows the deterministic setup, the weights, the loss methods, and an absolute ton of random functions that I let the AIs monkey patch in because it's faster than trying to teach AI 15 classes in 15 files.
|
| 33 |
- The patterns on this one struggle based on certain pentachora overlap which is why it had to be rewritten again.
|
|
|
|
|
|
|
| 34 |
|
| 35 |
## 🧠 Model overview
|
| 36 |
|
|
|
|
| 31 |
- I appreciate every single contributor to this - direct or indirect - through your invaluable contributions to science that manifested in utilizable AI form.
|
| 32 |
- I have included the training notebook as train_notebook.ipynb - which shows the deterministic setup, the weights, the loss methods, and an absolute ton of random functions that I let the AIs monkey patch in because it's faster than trying to teach AI 15 classes in 15 files.
|
| 33 |
- The patterns on this one struggle based on certain pentachora overlap which is why it had to be rewritten again.
|
| 34 |
+
- The deterministic and non-deterministic nature of the combination of utilities manifest quirks and behavior that are unexpected, which is why the deterministic version is required.
|
| 35 |
+
- Strict determinism can be enabled for a more robust and accurate recreation but I may have missed some seed any points in this earlier notebook.
|
| 36 |
|
| 37 |
## 🧠 Model overview
|
| 38 |
|