What is label smoothing and why is it used?

Updated May 17, 2026

Short answer

Label smoothing softens hard labels to improve generalization.

Deep explanation

Instead of using one-hot vectors, label smoothing assigns small probability mass to incorrect classes, reducing overconfidence and improving calibration.

Unlock with a Pro subscription to view this section.

View pricing

Real-world example

No real-world example available yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

Common mistakes

No common mistakes listed yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

Follow-up questions

No follow-up questions available yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

More Neural Networks interview questions

View all →