Multilayer Feedforward Networks are Universal Approximators.¶
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer Feedforward Networks are Universal Approximators. Neural Networks, 6080(89), 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¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:3a91a96a91ee · see in the full table