mirror of
https://github.com/Cian-H/symbolic_nn_tests.git
synced 2025-12-22 22:22:01 +00:00
minor correction to readme.md
This commit is contained in:
@@ -76,7 +76,7 @@ This is a testing sandbox for developing various methods of injecting symbolic k
|
||||
```math
|
||||
Loss = ( \alpha * { r }^2 + 1) * SmoothL1Loss
|
||||
```
|
||||
- Final adaptive semantic loss function tested was the following:
|
||||
- Final adaptive semantic loss function tested (called `positive_slope_linear_loss`) was the following:
|
||||
```math
|
||||
Loss = ( \alpha * { r }^2 + 1) * ( \frac{ 1 }{ \beta } * log( 1 + exp( \beta * \gamma * -m ) ) + 1 ) * SmoothL1Loss
|
||||
```
|
||||
|
||||
Reference in New Issue
Block a user