Update README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,8 @@ This will enable a new realm of experimentation and present it's own optimizatio
|
|
| 13 |
overhead that backprop requires due to the hierarchical climb and return structure.
|
| 14 |
|
| 15 |
This version was using the older geometric vocabulary system with standard backprop as a preliminary test and it didn't do very well.
|
| 16 |
-
The next will feature a fully robust cantor stairing system with the vit-beatrix cohesion and full learning k-simplex cantor stairway embeddings
|
|
|
|
| 17 |
|
| 18 |
Likely the followup variation will the full David-inspired shunt network that coalesces multiple Bert variants together while simultaneously acting as tiny
|
| 19 |
experts in a form of MOE that should enable at least 5 variants of alternative bert models to intercommunicate opinions.
|
|
|
|
| 13 |
overhead that backprop requires due to the hierarchical climb and return structure.
|
| 14 |
|
| 15 |
This version was using the older geometric vocabulary system with standard backprop as a preliminary test and it didn't do very well.
|
| 16 |
+
The next will feature a fully robust cantor stairing system with the vit-beatrix cohesion and full learning k-simplex cantor stairway embeddings,
|
| 17 |
+
this variation will still have backprop but there will be an additional head and complexity analysis tool for geometric stability testing with divergent pathways.
|
| 18 |
|
| 19 |
Likely the followup variation will the full David-inspired shunt network that coalesces multiple Bert variants together while simultaneously acting as tiny
|
| 20 |
experts in a form of MOE that should enable at least 5 variants of alternative bert models to intercommunicate opinions.
|