Construct · 1 fields · 1 citations

universal approximation theorem: 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

the result that a feedforward network with one hidden layer and enough units can approximate any continuous function to any accuracy.

In machine learning, universal approximation theorem refers to the result that a feedforward network with one hidden layer and enough units can approximate any continuous function to any accuracy. This meaning comes from Hornik (1989) in Neural Networks.[1]

Unit
Recovery means
Measured by

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

See how universal approximation theorem 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

accuracy3 fields · 6 citationsjingle · one word, three constructs continuity4 fields · 4 citationsjingle · one word, four constructs feedforward3 fields · 5 citationsjingle · one word, three constructs

References

Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359-366. https://doi.org/10.1016/0893-6080(89)90020-8

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