Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben
Neural Computing and Applications
Erschienen in: Neural Computing and Applications 9/2019

09.06.2018 | S.I. : Emergence in Human-like Intelligence towards Cyber-Physical Systems

Constructive function approximation by neural networks with optimized activation functions and fixed weights

verfasst von: Feng-Jun Li

Erschienen in: Neural Computing and Applications | Ausgabe 9/2019

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Our purpose in this paper is to construct three types of single-hidden layer feed-forward neural networks (FNNs) with optimized piecewise linear activation functions and fixed weights and to present the ideal upper and lower bound estimations on the approximation accuracy of the FNNs, for continuous function defined on bounded intervals. We also prove these three types of single-hidden layer FNNs can interpolate any bounded and measurable functions. Our approach compared with existing methods does not require training. Our conclusions not only uncover the inherent properties of approximation of the FNNs, but also reveal the latent relationship among the precision of approximation, the number of hidden units and the smoothness of the target function. Finally, we demonstrate some numerical results that show good agreement with theory.
Vorheriger Artikel Hybrid optimization algorithms by various structures for a real-world inverse scheduling problem with uncertain due-dates under single-machine shop systems
Nächster Artikel A new method of online extreme learning machine based on hybrid kernel function

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren
Literatur
1.
Cybenko G (1989) Approximation by superpositions of sigmoidal function. Math Control Signals Syst 2:303–314MathSciNetCrossRef
2.
Chen TP (1994) Approximation problems in system identification with neural networks. Sci China Ser A 24:1–7MathSciNet
3.
4.
Barhen J, Cogswell R, Protopopescu V (2000) Single iteration training algorithm for multilayer feedforward neural networks. Neural Process Lett 11:113–129CrossRef
5.
Ito Y, Saito K (1996) Superposition of linearly independent functions and finite mappings by neural networks. Math Sci 21:27–33MathSciNetMATH
6.
Ganjefar S, Tofighi M (2015) Single-hidden-layer fuzzy recurrent wavelet neural network: applications to function approximation and system identification. Inf Sci 294:269–285MathSciNetCrossRef
7.
Chen TP, Chen H (1995) Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to a dynamic system. IEEE Trans Neural Netw 6:911–917CrossRef
8.
Yoshifusa I (1991) Approximation of functions on a compact set by finite sums of sigmoid function without scaling. Neural Netw 4:817–826CrossRef
9.
Sartori MA, Antsaklis PJ (1991) A simple method to derive bounds on the size and to train multilayer neural networks. IEEE Trans Neural Netw 24:467–471CrossRef
10.
Hahm N, Hong BI (1999) Extension of localized approximation by neural networks. Bull Austral Math Soc 59:121–131MathSciNetCrossRef
11.
Chui CK, Li X (1992) Approximation by ridge functions and neural networks with one hidden Iayer. J Approx Theory 70:131–141MathSciNetCrossRef
12.
Ito Y (1991) Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Netw 4:385–394CrossRef
13.
Funahashi K (1989) On the approximate realization of continuous mapping by neural network. Neural Netw 2:183–192CrossRef
14.
Quéau LM, Kimiaei M, Randolph MF (2015) An analysis of global robust stability of delayed dynamical neural networks. Eng Struct 92:172–185CrossRef
15.
Li FJ (2011) Interpolation and convergence of Bernstein–B\(\acute{e}\)zier coefficients. Acta Math Sin Engl Ser 27:1769–1782MathSciNetCrossRef
16.
Cao FL, Lin SB, Xu ZB (2010) Approximation capability of interpolation neural networks. Neurocomputing 74:457–460CrossRef
17.
18.
Li X (2002) Interpolation by ridge polynomials and its application in neural networks. J Comput Appl Math 144:197–209MathSciNetCrossRef
19.
Llanas B, Sainz FJ (2006) Constructive approximate interpolation by neural networks. J Comput Appl Math 188:283–308MathSciNetCrossRef
20.
Llanas B, Lantarón S (2007) Hermite interpolation by neural networks. Appl Math Comput 191:429–4398MathSciNetMATH
21.
22.
Costarelli D (2014) Interpolation by neural network operators activated by ramp functions. J Math Anal Appl 419:574–582MathSciNetCrossRef
23.
Stinchcombe MB (1999) Neural network approximation of continuous functionals and continuous functions on compactifications. Neural Netw 12:467–477CrossRef
24.
Konovalov VN, Leviatan D, Maiorov VE (2009) Approximation of Sobolev classes by polynomials and ridge functions. J Approx Theory 159:97–108MathSciNetCrossRef
25.
Anastassiou GA (2002) Univariate sigmoidal neural network approximation. J Comput Anal Appl 14:659–690MathSciNetMATH
26.
Anastassiou GA (2011) Multivariate sigmoidal neural network approximation. Neural Netw 24:378–386CrossRef
27.
Anastassiou GA (2011) Multivariate hyperbolic tangent neural network approximation. Comput Math Appl 61:809–821MathSciNetCrossRef
28.
29.
Cao F, Chen Z (2012) The construction and approximation of a class of neural networks operators with ramp functions. J Comput Anal Appl 14:101–112MathSciNetMATH
30.
Cheang GHL (2010) Approximation with neural networks activated by ramp sigmoids. J Approx Theory 162:1450–1465MathSciNetCrossRef
31.
32.
Shristava Y, Dasgupta S (1990) Neural networks for exact matching of functions on a discrete domain. In: Proceedings of the 29th IEEE conference on decision and control. Honolulu, pp 1719–1724
33.
Huang GB, Babri HA (1998) Feedforward neural networks with arbitrary bounded nonlinear activation functions. IEEE Trans Neural Netw 9:224–229CrossRef
34.
Costarelli D, Spigler R (2015) Approximation by series of sigmoidal functions with application to neural networks. Ann Math Puraed Appl 194:289–306MathSciNetCrossRef
35.
Anastassiou GA (1997) Rate of convergence of some neural network operators to the unit-univariate case. J Math Anal Appl 212:237–262MathSciNetCrossRef
36.
Anastassiou GA (2011) Intelligent systems: approximation by artificial neural networks. In: Intelligent systems reference library, vol 19, Springer, Berlin
37.
Cao F, Chen Z (2016) Scattered data approximation by neural networks operators. Neurocomputing 190:237–242CrossRef
38.
Cao F, Chen Z (2015) The construction and approximation of feedforward neural network with hyperbolic tangent function. Appl Math A J Chin Univ 30:151–162MathSciNetCrossRef
39.
Cardaliaguet P, Euvrard G (1992) Approximation of a function and its derivative with a neural network. Neurak Netw 5:207–220CrossRef
40.
Costarelli D, Spigler R (2013) Multivariate neural network operators with sigmoidal activation functions. Neural Netw 48:72–77CrossRef
41.
Costarelli D, Spigler R (2014) Convergence of a family of neural network operators of the Kantorovich type. J Approx Theory 185:80–90MathSciNetCrossRef
42.
Tamura S, Tateishi M (1997) Capabilities of a four-layered feedforward neural network. IEEE Trans Neural Netw 8:251–255CrossRef
43.
Ismailov VE (2012) Approximation by neural networks with weights varying on a finite set of directions. J Math Anal Appl 389:72–83MathSciNetCrossRef
44.
Nageswara SVR (1999) Simple sample bound for feedforward sigmoid networks with bounded weights. Neuralcomputing 29:115–122CrossRef
45.
Hahm N, Hong BI (2004) An approximation by neural networks with a fixed weight. Comput Math Appl 47:1897–1903MathSciNetCrossRef
46.
Xu ZB, Cao FL (2004) The essential order of approximation for neural networks. Sci China 47:97–112MathSciNetMATH
47.
Xu ZB, Cao FL (2005) Simultaneous Lp-approximation order for neural networks. Neural Netw 18:914–923CrossRef
48.
Xu ZB, Wang JJ (2006) The essential order of approximation for nearly exponential type neural networks. Sci China 49:446–460MathSciNetCrossRef
49.
Lin SB, Cao FL, Xu ZB (2011) Essential rate for approximation by spherical neural networks. Neural Netw 24:752–758CrossRef
50.
Wang JJ, Xu ZB (2010) New study on neural networks: the essential order of approximation. Neural Netw 23:618–624CrossRef
51.
Li FJ, Xu ZB (2008) The estimation of simultaneous approximation order for neural networks. Chaos, Solitons Fractals 36:572–580MathSciNetCrossRef
52.
Li FJ, Xu ZB, Zhou YT (2008) The essential order of approximation for Suzuki’s neural networks. Neurocomputing 71:3525–3533CrossRef
53.
Li FJ, Xu ZB (2007) The essential order of simultaneous approximation for neural networks. Appl Math Comput 194:120–127MathSciNetMATH
54.
Butzer PL, Nessel RJ (1971) Fourier analysis and approximation. Pure Appl Math. Academic Press, New YorkCrossRef
55.
Ditzian Z, Totik V (1987) Moduli of smoothness SSCM. Springer, BerlinCrossRef
56.
Suzuki S (1998) Constructive function approximation by three layer artificial neural networks. Neural Netw 11:1049–1058CrossRef
57.
Chui CK, Li X, Mhaskar HN (2006) Limitations of the approximation capabilities of neural networks with one hidden layer. Adv Comput Math 5:233–243MathSciNetCrossRef
58.
Ismailov VE (2014) On the approximation by neural networks with bounded number of neurons in hidden layers. J Math Anal Appl 417:963–969MathSciNetCrossRef
59.
Arteaga C, Marrero I (2015) Wiener’s tauberian theorems for the FourierCBessel transformation and uniform approximation by RBF networks of Delsarte translates. J Math Anal Appl 431:482–493MathSciNetCrossRef
60.
Costarelli D, Spigler R (2013) Approximation results for neural network operators activated by sigmoidal functions. Neural Netw 44:101–106CrossRef
61.
Yang S, Ting TO, Man KL, Gua SU (2013) Investigation of neural networks for function approximation. Proc Comput Sci 17:586–594CrossRef
62.
63.
Bordignon F, Gomide F (2014) Uninorm based evolving neural networks and approximation capabilities. Neurocomputing 127:13–20CrossRef
64.
Vukovi N, Miljkovi Z (2013) A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation. Neural Netw 46:210–226CrossRef
65.
Costarelli D (2015) Neural network operators: Constructive interpolation of multivariate functions. Neural Netw 67:28–36CrossRef
66.
Anastassiou GA (2011) Univariate hyperbolic tangent neural network approximation. Math Comput Modell 53:1111–1132MathSciNetCrossRef
67.
Ditzian Z (1989) Best polynomial approximation and Bernstein polynomial approximation on a simplex. Proc Kon Nederl Akad Wetensch 92:243–256MathSciNetCrossRef
68.
Berens H, Xu Y (1991) K-moduli, moduli of smoothness, and Bernstein polynomials on a simplex. Indag Mathem NS 4:411–421MathSciNetCrossRef
69.
Phillips GM (2003) Interpolation and approximation by polynomials. Springer, New YorkCrossRef
Metadaten
Titel
Constructive function approximation by neural networks with optimized activation functions and fixed weights
verfasst von
Feng-Jun Li
Publikationsdatum
09.06.2018
Verlag
Springer London
Erschienen in
Neural Computing and Applications / Ausgabe 9/2019
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI
https://doi.org/10.1007/s00521-018-3573-3

Weitere Artikel der Ausgabe 9/2019

Neural Computing and Applications 9/2019 Zur Ausgabe

S.I. : Emergence in Human-like Intelligence towards Cyber-Physical Systems

Time series clustering based on sparse subspace clustering algorithm and its application to daily box-office data analysis

Original Article

Vibration prediction in drilling processes with HSS and carbide drill bit by means of artificial neural networks

S.I. : Emergence in Human-like Intelligence towards Cyber-Physical Systems

Deep learning of system reliability under multi-factor influence based on space fault tree

Original Article

A novel quick seizure detection and localization through brain data mining on ECoG dataset

Original Article

Speed limit sign detection and recognition system using SVM and MNIST datasets

Original Article

State observer-based adaptive neural dynamic surface control for a class of uncertain nonlinear systems with input saturation using disturbance observer