Approximation results for neural network operators activated by sigmoidal functions
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883 · cited 3×
“Neural networks play a fundamental role in many models, the activation function σ is usually a sigmoidal function, and they are extensively used in Approximation Theory (Barron, 1993; Chen, 1993; Costarelli & Spigler, submitted for publcation-b; Cybenko, 1989; Gao & Xu, 1993; Girosi & Anzellotti, 1993; Gnecco, 2012; G…”
Universal approximation bounds for superpositions of a sigmoidal function
Barron, A. R. (1993) · IEEE Transactions on Information Theory · doi:10.1109/18.256500 · Cited by 2,804 · cited 4×
“Neural networks play a fundamental role in many models, the activation function σ is usually a sigmoidal function, and they are extensively used in Approximation Theory (Barron, 1993; Chen, 1993; Costarelli & Spigler, submitted for publcation-b; Cybenko, 1989; Gao & Xu, 1993; Girosi & Anzellotti, 1993; Gnecco, 2012; G…”
BackgroundMethodInfluentialApproximation theory of the MLP model in neural networks
Pinkus, A. (1999) · Acta Numerica · doi:10.1017/s0962492900002919 · Cited by 1,529 · cited 1×
“…denotes the inner product in Rs, and σ is the activation function of the network, see Chui and Li (1992), Costarelli and Spigler (submitted for publication-a), Jones (1988), Lenze (1992), Li (1996), Light (1993), Li andMicchelli (2000), Makovoz (1998), Mhaskar andMicchelli (1995) and Pinkus (1999).”
BackgroundApproximation by superposition of sigmoidal and radial basis functions
Mhaskar, H. N., & Micchelli, C. A. (1992) · Advances in Applied Mathematics · doi:10.1016/0196-8858(92)90016-p · Cited by 257 · cited 2×
“In particular, in Barron (1993) and Mhaskar and Micchelli (1992, 1995), the Lp-norm errors made in such approximations have been studied and related to the number of neurons in the networks.”
BackgroundThe approximation operators with sigmoidal functions
Chen, Z., & Cao, F. (2009) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2009.05.001 · Cited by 251 · cited 3×
“We define the so-called quasi-interpolation operators Gn(f , x) := k∈Z f k n φσ (nx − k), x ∈ R, for every n > 0, see, e.g., Anastassiou (2011d, 2012) and Cao and Chen (2009).”
BackgroundArtificial neural networks for speech and vision
Mammone, R. J. (1994) · Cited by 231
Approximation by ridge functions and neural networks with one hidden layer
Chui, C. K., & Li, X. (1992) · Journal of Approximation Theory · doi:10.1016/0021-9045(92)90081-x · Cited by 179 · cited 3×
“…the threshold values, aj ∈ Rs are the weights, cj are the coefficients; aj · x denotes the inner product in Rs, and σ is the activation function of the network, see Chui and Li (1992), Costarelli and Spigler (submitted for publication-a), Jones (1988), Lenze (1992), Li (1996), Light (1993), Li…”
BackgroundInfluentialMultivariate sigmoidal neural network approximation
Anastassiou, G. A. (2011) · Neural Networks · doi:10.1016/j.neunet.2011.01.003 · Cited by 175 · cited 9×
“Subsequently, Anastassiou studied neural network operators activated by the hyperbolic tangent (σh), and the logistic sigmoidal function (σℓ), in both the univariate and multivariate cases, see Anastassiou (2011a, 2011b, 2011c, 2011d, 2012).”
BackgroundMethodResultInfluentialIntelligent Systems: Approximation by Artificial Neural Networks
Anastassiou, G. A. (2011) · Intelligent systems reference library · doi:10.1007/978-3-642-21431-8 · Cited by 166 · cited 10×
“Subsequently, Anastassiou studied neural network operators activated by the hyperbolic tangent (σh), and the logistic sigmoidal function (σℓ), in both the univariate and multivariate cases, see Anastassiou (2011a, 2011b, 2011c, 2011d, 2012).”
BackgroundMethodResultInfluentialUnivariate hyperbolic tangent neural network approximation
Anastassiou, G. A. (2010) · Mathematical and Computer Modelling · doi:10.1016/j.mcm.2010.11.072 · Cited by 155 · cited 9×
“Subsequently, Anastassiou studied neural network operators activated by the hyperbolic tangent (σh), and the logistic sigmoidal function (σℓ), in both the univariate and multivariate cases, see Anastassiou (2011a, 2011b, 2011c, 2011d, 2012).”
BackgroundMethodResultInfluentialDegree of Approximation by Neural and Translation Networks with a Single Hidden Layer
Mhaskar, H. N., & Micchelli, C. A. (1995) · Advances in Applied Mathematics · doi:10.1006/aama.1995.1008 · Cited by 155 · cited 1×
“In particular, in Barron (1993) and Mhaskar and Micchelli (1992, 1995), the Lp-norm errors made in such approximations have been studied and related to the number of neurons in the networks.”
BackgroundLi, X. (1996) · Neurocomputing · doi:10.1016/0925-2312(95)00070-4 · Cited by 120 · cited 1×
“…denotes the inner product in Rs, and σ is the activation function of the network, see Chui and Li (1992), Costarelli and Spigler (submitted for publication-a), Jones (1988), Lenze (1992), Li (1996), Light (1993), Li andMicchelli (2000), Makovoz (1998), Mhaskar andMicchelli (1995) and Pinkus (1999).”
BackgroundMultivariate hyperbolic tangent neural network approximation
Anastassiou, G. A. (2011) · Computers & Mathematics with Applications · doi:10.1016/j.camwa.2010.12.029 · Cited by 118 · cited 9×
“Subsequently, Anastassiou studied neural network operators activated by the hyperbolic tangent (σh), and the logistic sigmoidal function (σℓ), in both the univariate and multivariate cases, see Anastassiou (2011a, 2011b, 2011c, 2011d, 2012).”
BackgroundMethodResultInfluentialUniform Approximation by Neural Networks
Makovoz, Y. (1998) · Journal of Approximation Theory · doi:10.1006/jath.1997.3217 · Cited by 116 · cited 1×
“…denotes the inner product in Rs, and σ is the activation function of the network, see Chui and Li (1992), Costarelli and Spigler (submitted for publication-a), Jones (1988), Lenze (1992), Li (1996), Light (1993), Li andMicchelli (2000), Makovoz (1998), Mhaskar andMicchelli (1995) and Pinkus (1999).”
BackgroundDEGREE OF APPROXIMATION BY SUPERPOSITIONS OF A SIGMOIDAL FUNCTION
Chen, & Debao (1993) · Acta Scientiarum Naturalium Universitatis Sunyatseni · Cited by 48
Approximation with neural networks activated by ramp sigmoids
Cheang, G. H. L. (2010) · Journal of Approximation Theory · doi:10.1016/j.jat.2010.03.004 · Cited by 40
Complexity estimates based on integral transforms induced by computational units
Kůrková, V. (2012) · Neural Networks · doi:10.1016/j.neunet.2012.05.002 · Cited by 37 · cited 2×
“Neural networks play a fundamental role in many models, the activation function σ is usually a sigmoidal function, and they are extensively used in Approximation Theory (Barron, 1993; Chen, 1993; Costarelli & Spigler, submitted for publcation-b; Cybenko, 1989; Gao & Xu, 1993; Girosi & Anzellotti, 1993; Gnecco, 2012; G…”
On a Variational Norm Tailored to Variable-Basis Approximation Schemes
Gnecco, G., & Sanguineti, M. (2010) · IEEE Transactions on Information Theory · doi:10.1109/tit.2010.2090198 · Cited by 29 · cited 1×
“…Theory (Barron, 1993; Chen, 1993; Costarelli & Spigler, submitted for publcation-b; Cybenko, 1989; Gao & Xu, 1993; Girosi & Anzellotti, 1993; Gnecco, 2012; Gnecco & Sanguineti, 2011; Hahm & Hong, 2002; Kainen & Kurková, 2009; Kurková, 2012; Lewicki & Marino, 2003, 2004; Mhaskar & Micchelli, 1992).”
Approximation order to a function in ( ) by superposition of a sigmoidal function
Hong, B. I., & Hahm, N. (2002) · Applied Mathematics Letters · doi:10.1016/s0893-9659(02)80011-8 · Cited by 26 · cited 1×
“…Theory (Barron, 1993; Chen, 1993; Costarelli & Spigler, submitted for publcation-b; Cybenko, 1989; Gao & Xu, 1993; Girosi & Anzellotti, 1993; Gnecco, 2012; Gnecco & Sanguineti, 2011; Hahm & Hong, 2002; Kainen & Kurková, 2009; Kurková, 2012; Lewicki & Marino, 2003, 2004; Mhaskar & Micchelli, 1992).”
Metadata
- Authors
- Costarelli, D., & Spigler, R.
- Venue
- Neural Networks
- Publisher
- Elsevier BV
- Published
- 2013-08
- Volume
- 44
- Pages
- 101-106
- ISSN
- 0893-6080 (ISSN-L)
- OpenAlex
- W1986164709
- Cited by
- 198
- References
- 19
- FWCI
- 12.62
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.