mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-24 13:54:31 +00:00
Add MAX_GRAD constant (1e6) and clip gradients in BCE and CrossEntropy backward passes to prevent gradient explosion with extreme prediction values near 0 or 1. Also add examples/loss_demo.rs for manual testing and demonstration of loss function behavior. |
||
|---|---|---|
| .. | ||
| loss_demo.rs | ||