Constructive Approximation by Superposition of Sigmoidal Functions

Constructive Approximation by Superposition of Sigmoidal Functions

Year:    2013

Analysis in Theory and Applications, Vol. 29 (2013), Iss. 2 : pp. 169–196

Abstract

In this paper, a constructive theory is developed for approximating functions of one or more variables by superposition of sigmoidal functions. This is done in the uniform norm as well as in the $L^p$ norm. Results for the simultaneous approximation, with the same order of accuracy, of a function and its derivatives (whenever these exist), are obtained. The relation with neural networks and radial basis functions approximations is discussed. Numerical examples are given for the purpose of illustration.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/ata.2013.v29.n2.8

Analysis in Theory and Applications, Vol. 29 (2013), Iss. 2 : pp. 169–196

Published online:    2013-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    28

Keywords:    Sigmoidal functions multivariate approximation $L^p$ approximation neural networks radial basis functions.

  1. Approximation by network operators with logistic activation functions

    Chen, Zhixiang | Cao, Feilong | Hu, Jinjie

    Applied Mathematics and Computation, Vol. 256 (2015), Iss. P.565

    https://doi.org/10.1016/j.amc.2015.01.049 [Citations: 7]
  2. Solving numerically nonlinear systems of balance laws by multivariate sigmoidal functions approximation

    Costarelli, Danilo | Spigler, Renato

    Computational and Applied Mathematics, Vol. 37 (2018), Iss. 1 P.99

    https://doi.org/10.1007/s40314-016-0334-8 [Citations: 12]
  3. A note on the Unit–Rayleigh “adaptive function”

    Vasileva, Maria | Malinova, Anna | Rahneva, Olga | Angelova, Evgenia

    EIGHTH INTERNATIONAL CONFERENCE NEW TRENDS IN THE APPLICATIONS OF DIFFERENTIAL EQUATIONS IN SCIENCES (NTADES2021), (2022), P.030039

    https://doi.org/10.1063/5.0083539 [Citations: 1]
  4. On Sharpness of Error Bounds for Univariate Approximation by Single Hidden Layer Feedforward Neural Networks

    Goebbels, Steffen

    Results in Mathematics, Vol. 75 (2020), Iss. 3

    https://doi.org/10.1007/s00025-020-01239-8 [Citations: 8]
  5. New Trends in the Applications of Differential Equations in Sciences

    A Note on the Hwang-Kim’s Universal Activation Function

    Vasileva, Maria | Kyurkchiev, Nikolay

    2024

    https://doi.org/10.1007/978-3-031-53212-2_40 [Citations: 0]
  6. Three novel bird strike likelihood modelling techniques: The case of Brisbane Airport, Australia

    Andrews, Robert | Bevrani, Bayan | Colin, Brigitte | Wynn, Moe T. | ter Hofstede, Arthur H. M. | Ring, Jackson | Pérez-García, Juan Manuel

    PLOS ONE, Vol. 17 (2022), Iss. 12 P.e0277794

    https://doi.org/10.1371/journal.pone.0277794 [Citations: 1]
  7. Local Sigmoid Method: Non-Iterative Deterministic Learning Algorithm for Automatic Model Construction of Neural Network

    Alfarozi, Syukron Abu Ishaq | Pasupa, Kitsuchart | Sugimoto, Masanori | Woraratpanya, Kuntpong

    IEEE Access, Vol. 8 (2020), Iss. P.20342

    https://doi.org/10.1109/ACCESS.2020.2968983 [Citations: 7]
  8. Approximation by series of sigmoidal functions with applications to neural networks

    Costarelli, Danilo | Spigler, Renato

    Annali di Matematica Pura ed Applicata (1923 -), Vol. 194 (2015), Iss. 1 P.289

    https://doi.org/10.1007/s10231-013-0378-y [Citations: 36]
  9. Uniform approximation rates and metric entropy of shallow neural networks

    Ma, Limin | Siegel, Jonathan W. | Xu, Jinchao

    Research in the Mathematical Sciences, Vol. 9 (2022), Iss. 3

    https://doi.org/10.1007/s40687-022-00346-y [Citations: 3]
  10. Frontiers in Functional Equations and Analytic Inequalities

    Error Estimation for Approximate Solutions of Delay Volterra Integral Equations

    Duman, Oktay

    2019

    https://doi.org/10.1007/978-3-030-28950-8_29 [Citations: 0]
  11. On the Hausdorff distance between the Heaviside step function and Verhulst logistic function

    Kyurkchiev, Nikolay | Markov, Svetoslav

    Journal of Mathematical Chemistry, Vol. 54 (2016), Iss. 1 P.109

    https://doi.org/10.1007/s10910-015-0552-0 [Citations: 51]
  12. A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function

    Guliyev, Namig J. | Ismailov, Vugar E.

    Neural Computation, Vol. 28 (2016), Iss. 7 P.1289

    https://doi.org/10.1162/NECO_a_00849 [Citations: 62]
  13. A note on the xgamma cumulative sigmoid. Some applications

    Angelova, Evgenia | Malinova, Anna | Kyurkchiev, Vesselin | Rahneva, Olga

    RENEWABLE ENERGY SOURCES AND TECHNOLOGIES, (2019), P.030001

    https://doi.org/10.1063/1.5127466 [Citations: 0]
  14. Max-product neural network and quasi-interpolation operators activated by sigmoidal functions

    Costarelli, Danilo | Vinti, Gianluca

    Journal of Approximation Theory, Vol. 209 (2016), Iss. P.1

    https://doi.org/10.1016/j.jat.2016.05.001 [Citations: 57]
  15. A collocation method for solving nonlinear Volterra integro-differential equations of neutral type by sigmoidal functions

    Costarelli, Danilo | Spigler, Renato

    Journal of Integral Equations and Applications, Vol. 26 (2014), Iss. 1

    https://doi.org/10.1216/JIE-2014-26-1-15 [Citations: 35]
  16. Mathematical Analysis and Computing

    Max-Product Type Exponential Neural Network Operators

    Bajpeyi, Shivam | Kumar, A. Sathish

    2021

    https://doi.org/10.1007/978-981-33-4646-8_44 [Citations: 2]
  17. Measure Theoretic Results for Approximation by Neural Networks with Limited Weights

    Ismailov, Vugar E. | Savas, Ekrem

    Numerical Functional Analysis and Optimization, Vol. 38 (2017), Iss. 7 P.819

    https://doi.org/10.1080/01630563.2016.1254654 [Citations: 4]
  18. Quantifying urban spatial resilience using multi-criteria decision analysis (MCDA) and back propagation neural network (BPNN)

    Lu, Yuwen | Zhai, Guofang | Zhai, Wei

    International Journal of Disaster Risk Reduction, Vol. 111 (2024), Iss. P.104694

    https://doi.org/10.1016/j.ijdrr.2024.104694 [Citations: 1]
  19. An interval uncertainty analysis method for structural response bounds using feedforward neural network differentiation

    Wang, Liqun | Chen, Zengtao | Yang, Guolai

    Applied Mathematical Modelling, Vol. 82 (2020), Iss. P.449

    https://doi.org/10.1016/j.apm.2020.01.059 [Citations: 23]
  20. Neural network operators: Constructive interpolation of multivariate functions

    Costarelli, Danilo

    Neural Networks, Vol. 67 (2015), Iss. P.28

    https://doi.org/10.1016/j.neunet.2015.02.002 [Citations: 52]
  21. Insights on the different convergences in Extreme Learning Machine

    De Falco, Davide Elia | Calabrò, Francesco | Pragliola, Monica

    Neurocomputing, Vol. 599 (2024), Iss. P.128061

    https://doi.org/10.1016/j.neucom.2024.128061 [Citations: 0]
  22. Bifurcation in car-following models with time delays and driver and mechanic sensitivities

    Padial, Juan Francisco | Casal, Alfonso

    Revista de la Real Academia de Ciencias Exactas, Físicas y Naturales. Serie A. Matemáticas, Vol. 116 (2022), Iss. 4

    https://doi.org/10.1007/s13398-022-01307-4 [Citations: 2]
  23. Interpolation by neural network operators activated by ramp functions

    Costarelli, Danilo

    Journal of Mathematical Analysis and Applications, Vol. 419 (2014), Iss. 1 P.574

    https://doi.org/10.1016/j.jmaa.2014.05.013 [Citations: 44]
  24. Error Estimate for Spherical Neural Networks Interpolation

    Lin, Shaobo | Zeng, Jinshan | Xu, Zongben

    Neural Processing Letters, Vol. 42 (2015), Iss. 2 P.369

    https://doi.org/10.1007/s11063-014-9361-x [Citations: 6]
  25. On the approximation by single hidden layer feedforward neural networks with fixed weights

    Guliyev, Namig J. | Ismailov, Vugar E.

    Neural Networks, Vol. 98 (2018), Iss. P.296

    https://doi.org/10.1016/j.neunet.2017.12.007 [Citations: 88]
  26. A Neural Network Approximation Based on a Parametric Sigmoidal Function

    Yun, Beong In

    Mathematics, Vol. 7 (2019), Iss. 3 P.262

    https://doi.org/10.3390/math7030262 [Citations: 8]
  27. Approximation capability of two hidden layer feedforward neural networks with fixed weights

    Guliyev, Namig J. | Ismailov, Vugar E.

    Neurocomputing, Vol. 316 (2018), Iss. P.262

    https://doi.org/10.1016/j.neucom.2018.07.075 [Citations: 46]
  28. Multivariate neural network interpolation operators

    Kadak, Uğur

    Journal of Computational and Applied Mathematics, Vol. 414 (2022), Iss. P.114426

    https://doi.org/10.1016/j.cam.2022.114426 [Citations: 18]
  29. Convergence of a family of neural network operators of the Kantorovich type

    Costarelli, Danilo | Spigler, Renato

    Journal of Approximation Theory, Vol. 185 (2014), Iss. P.80

    https://doi.org/10.1016/j.jat.2014.06.004 [Citations: 59]
  30. Multivariate neural network operators with sigmoidal activation functions

    Costarelli, Danilo | Spigler, Renato

    Neural Networks, Vol. 48 (2013), Iss. P.72

    https://doi.org/10.1016/j.neunet.2013.07.009 [Citations: 97]
  31. Comments on the Epsilon and Omega cumulative distributions: “Saturation in the Hausdorff sense”

    Kyurkchiev, Nikolay

    SEVENTH INTERNATIONAL CONFERENCE ON NEW TRENDS IN THE APPLICATIONS OF DIFFERENTIAL EQUATIONS IN SCIENCES (NTADES 2020), (2021), P.030020

    https://doi.org/10.1063/5.0040120 [Citations: 0]
  32. Fractional Approximation of Broad Learning System

    Wu, Shujun | Wang, Jian | Sun, Huaying | Zhang, Kai | Pal, Nikhil R.

    IEEE Transactions on Cybernetics, Vol. 54 (2024), Iss. 2 P.811

    https://doi.org/10.1109/TCYB.2021.3127152 [Citations: 22]
  33. A new interval perturbation method for static structural response bounds using radial basis neural network differentiation

    Yao, Yuwei | Wang, Liqun | Yang, Guolai | Xu, Fengjie | Li, Lei

    Journal of Mechanical Science and Technology, Vol. 37 (2023), Iss. 3 P.1389

    https://doi.org/10.1007/s12206-023-0225-z [Citations: 0]
  34. Some density results by deep Kantorovich type neural network operators

    Sharma, Manju | Singh, Uaday

    Journal of Mathematical Analysis and Applications, Vol. 533 (2024), Iss. 2 P.128009

    https://doi.org/10.1016/j.jmaa.2023.128009 [Citations: 4]
  35. Solving Volterra integral equations of the second kind by sigmoidal functions approximation

    Costarelli, Danilo | Spigler, Renato

    Journal of Integral Equations and Applications, Vol. 25 (2013), Iss. 2

    https://doi.org/10.1216/JIE-2013-25-2-193 [Citations: 32]
  36. A sigmoid method for some nonlinear Fredholm integral equations of the second kind

    Azevedo, Juarez S.

    Applied Numerical Mathematics, Vol. 181 (2022), Iss. P.125

    https://doi.org/10.1016/j.apnum.2022.05.014 [Citations: 3]
  37. Scattered data approximation by neural networks operators

    Chen, Zhixiang | Cao, Feilong

    Neurocomputing, Vol. 190 (2016), Iss. P.237

    https://doi.org/10.1016/j.neucom.2016.01.013 [Citations: 23]