Graham McIntire 08e4b9abdd Bigger network (128→64→32) and percentile-based training target ... - 3 hidden layers instead of 2 for better feature interaction learning - Target is within-band distance percentile (0-1) instead of raw normalized distance — reduces noise from operator/equipment variation		2026-04-01 09:17:36 -05:00
..
tasks	Bigger network (128→64→32) and percentile-based training target	2026-04-01 09:17:36 -05:00