w1n5t0n c8d7779699 feat(nisps-core,wasm): add per-sample weights to MLP training ...

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.

2026-04-02 20:35:24 +01:00

33 KiB

Executable file

Raw History

View raw