Construct · 1 fields · 1 citations

label smoothing: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Machine learning

replacing one-hot training targets with a mixture of the true label and a uniform distribution, discouraging overconfident predictions.

In machine learning, label smoothing refers to replacing one-hot training targets with a mixture of the true label and a uniform distribution, discouraging overconfident predictions. This meaning comes from Szegedy (2016) in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how label smoothing sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

distribution2 fields · 2 citationsjingle · one word, two constructs learning6 fields · 14 citationsjingle · one name, six constructs mixture2 fields · 2 citationsjingle · one word, two constructs

References

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the Inception Architecture for Computer Vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2016.308

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct