c8d7779699
Add optional sample_weights parameter to MLP::Train() and the WASM nisps_mlp_train binding. When provided, weights replace the uniform 1/N scaling per sample — enabling recency, spatial, or any custom importance weighting without changing the training interface. |
||
|---|---|---|
| .. | ||
| dataset.hpp | ||
| dataset_impl.hpp | ||
| iml.hpp | ||
| iml_impl.hpp | ||
| layer.hpp | ||
| loss.hpp | ||
| mlp.hpp | ||
| mlp_impl.hpp | ||
| nisps.hpp | ||
| node.hpp | ||
| sample.hpp | ||
| utils.hpp | ||