AbstractPhil commited on
Commit
5b6c95e
·
verified ·
1 Parent(s): ec63a3e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
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