Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,9 @@ license: apache-2.0
|
|
| 6 |
|
| 7 |
BCE loss isn't the best catalyst for geometry but it does work to funnel through an aligned transformer.
|
| 8 |
|
| 9 |
-
I underestimated the complexity of associative cross-modal differences, but it is converging.
|
|
|
|
|
|
|
| 10 |
|
| 11 |
If this fails to meet direct expectations, I'll form a proper hub and teach using the bertenstein method.
|
| 12 |
|
|
|
|
| 6 |
|
| 7 |
BCE loss isn't the best catalyst for geometry but it does work to funnel through an aligned transformer.
|
| 8 |
|
| 9 |
+
I underestimated the complexity of associative cross-modal differences, but it is converging. Shared space is a very tricky
|
| 10 |
+
catalyst to teach as an associative connection. Routing is easy, distilling is not as easy with multimodal structures and multiple
|
| 11 |
+
adjacent representations used as loss learning targets.
|
| 12 |
|
| 13 |
If this fails to meet direct expectations, I'll form a proper hub and teach using the bertenstein method.
|
| 14 |
|