AbstractPhil commited on
Commit
9673bc2
·
verified ·
1 Parent(s): e9e6a78

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -38,6 +38,13 @@ A geometric deep learning architecture using **Möbius wave interference lenses*
38
 
39
  MobiusNet learns frequency-selective sparse coding through three drifting wave functions (L, M, R) combined via learnable XOR/AND logic. The architecture progressively sharpens selectivity through depth, culminating in near-binary winner-take-all gating at the final block.
40
 
 
 
 
 
 
 
 
41
  ### Wave Interference Mechanism
42
 
43
  Each Möbius Lens computes:
 
38
 
39
  MobiusNet learns frequency-selective sparse coding through three drifting wave functions (L, M, R) combined via learnable XOR/AND logic. The architecture progressively sharpens selectivity through depth, culminating in near-binary winner-take-all gating at the final block.
40
 
41
+ ## Primary Concerns
42
+
43
+ The flops are considerably higher than alternative variations. The system DOES WORK, and it does improve the output, but the training time is higher due to the twist in/twist out architectural advantage.
44
+ In the process, you introduce additional uncertainty due to the nature of differentiation. The input must be controlled during distillation and the output must be catered.
45
+
46
+ This experiment was successful, but the optimization isn't there yet to provide a useful solution.
47
+
48
  ### Wave Interference Mechanism
49
 
50
  Each Möbius Lens computes: