Construct · 1 fields · 1 citations

He initialization: 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

setting initial weights with variance scaled to two over the number of inputs, derived so signals neither shrink nor explode in deep rectifier networks.

In machine learning, He initialization refers to setting initial weights with variance scaled to two over the number of inputs, derived so signals neither shrink nor explode in deep rectifier networks. This meaning comes from He (2015) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how He initialization 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

learning6 fields · 14 citationsjingle · one name, six constructs number3 fields · 6 citationsjingle · one word, three constructs variance4 fields · 6 citationsjingle · one word, four constructs

References

He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. arXiv. https://doi.org/10.48550/arxiv.1502.01852

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