Multilayer Feedforward Networks are Universal Approximators.¶
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer Feedforward Networks are Universal Approximators. Neural Networks, 2(5), 359-366.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Approximation
- The universal approximation properties of neural networks (Hornik (1989)
This sourceProof that feedforward networks with one hidden layer approximate any Borel-measurable function arbitrarily well.
- The universal approximation properties of neural networks (Hornik (1989)
- Dense Set
- In machine learning, generalization over a region demands training samples dense in that region in the relevant feature geometry — "out-of-distribution" is the explicit failure of density, and universal-approximation theorems are density statements about model classes.
This sourceUniversal-approximation result stated as a density statement about a model class in function space.
- In machine learning, generalization over a region demands training samples dense in that region in the relevant feature geometry — "out-of-distribution" is the explicit failure of density, and universal-approximation theorems are density statements about model classes.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Not recorded. Neither this nor any other of the 2 citations of this work carries a recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:3a91a96a91ee · see in the full table