Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

label

The class you assert for one training example, such as "tap".

A label is the target value attached to an example; a supervised model is trained to reproduce labels, including wrong ones.

Examples

  • The logger asks for the label before recording, so a window recorded after choosing 3 prints as one CSV line starting with "tap" followed by its 150 numbers.

  • A "tap" window with no spike in it is a wrong label and should be deleted, not kept.

See also

label noise class balance leakage
Read the full section →