Construct · 1 fields · 1 citations

random-label memorization: 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

deep networks can fit training sets with completely random labels, showing that classical capacity measures do not explain their generalization.

In machine learning, random-label memorization refers to deep networks can fit training sets with completely random labels, showing that classical capacity measures do not explain their generalization. This meaning comes from Zhang (2016) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how random-label memorization 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

capacity5 fields · 8 citationsjingle · one word, four limits generalization6 fields · 16 citationsjingle · one name, six constructs learning6 fields · 14 citationsjingle · one name, six constructs

References

Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2016). Understanding deep learning requires rethinking generalization. arXiv. https://doi.org/10.48550/arxiv.1611.03530

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