Universal approximation bounds for superpositions of a sigmoidal function

Andrew R. Barron

doi:https://doi.org/10.1109/18.256500

Universal approximation bounds for superpositions of a sigmoidal function

1993 · IEEE Transactions on Information Theory · 2,880 citations · 7 from inside this corpus

The source holds an abstract for this work, but its best open-access copy is under no open licence, which does not permit us to republish the text. Read it at the source below.

9 of 9 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

Artificial neural networks: fundamentals, computing, design, and application→Universal approximation bounds for superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Universal Approximation using Incremental Constructive Feedforward Networks with Random H…→Universal approximation bounds for superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Boosting the margin: a new explanation for the effectiveness of voting methods→Universal approximation bounds for superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Wavelet networks→Universal approximation bounds for superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Extreme learning machines: a survey→Universal approximation bounds for superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Nonlinear black-box modeling in system identification: a unified overview→Universal approximation bounds for superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Approximation theory of the MLP model in neural networks→Universal approximation bounds for superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Universal approximation bounds for superpositions of a sigmoidal function→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable
Universal approximation bounds for superpositions of a sigmoidal function→Approximation by superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Extreme learning machines: a survey→Approximation by superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Extreme learning machines: a survey→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable
Extreme learning machines: a survey→Universal Approximation using Incremental Constructive Feedforward Networks with Random H…Legacy edge — source detail unavailable
Nonlinear black-box modeling in system identification: a unified overview→Approximation by superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Nonlinear black-box modeling in system identification: a unified overview→Wavelet networksLegacy edge — source detail unavailable
Approximation by superpositions of a sigmoidal function→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable
Multilayer feedforward networks are universal approximators→Approximation by superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Universal Approximation using Incremental Constructive Feedforward Networks with Random H…→Approximation by superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Universal Approximation using Incremental Constructive Feedforward Networks with Random H…→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable
Approximation theory of the MLP model in neural networks→Approximation by superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Approximation theory of the MLP model in neural networks→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable
Wavelet networks→Approximation by superpositions of a sigmoidal functionLegacy edge — source detail unavailable
Wavelet networks→Multilayer feedforward networks are universal approximatorsLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
Multilayer feedforward networks are universal approximators	1989	21,633
Approximation by superpositions of a sigmoidal function	1989	13,884

What cites it, inside the corpus

Paper	Year	Cited
Artificial neural networks: fundamentals, computing, design, and application	2000	3,250
Universal Approximation using Incremental Constructive Feedforward Networks with Random H…	2006	2,636
Boosting the margin: a new explanation for the effectiveness of voting methods	1998	2,344
Wavelet networks	1992	2,099
Extreme learning machines: a survey	2011	1,932
Nonlinear black-box modeling in system identification: a unified overview	1995	1,930
Approximation theory of the MLP model in neural networks	1999	1,548

Links

Download BibTeX · Download RIS · DOI · OpenAlex record

Topics

Neural Networks and Applications	Computer Science
Model Reduction and Neural Networks	Physics and Astronomy
Advanced Numerical Analysis Techniques	Engineering

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports1 author record(s) attached.
supports30 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:48+00:00.

sha256 46f669157f96ea35…