Pointwise and uniform approximation by multivariate neural network operators of the max-product type

Neural Networks

Volumn 81, Issue , 2016, Pages 81-90

  Costarelli, Danilo ^a   Vinti, Gianluca ^a  

^a UNIVERSITY OF PERUGIA   (Italy)

Author keywords

Max product operators; Multivariate neural networks operators; Order of approximation; Sigmoidal functions; Uniform approximation

Indexed keywords

ARTIFICIAL INTELLIGENCE; COGNITIVE SYSTEMS; NEURAL NETWORKS;

MAX-PRODUCT; NEURAL NETWORK (NN); ORDER OF APPROXIMATION; QUASI-INTERPOLATION; RATE OF CONVERGENCE; SIGMOIDAL ACTIVATION FUNCTIONS; SIGMOIDAL FUNCTIONS; UNIFORM APPROXIMATION;

APPROXIMATION THEORY;

ARTICLE; ARTIFICIAL NEURAL NETWORK; BIVARIATE ANALYSIS; DENSITY FUNCTIONAL THEORY; MATHEMATICAL COMPUTING; MATHEMATICAL VARIABLE; MULTIVARIATE ANALYSIS; MULTIVARIATE MAX PRODUCT NEURAL NETWORK; PRIORITY JOURNAL; QUASI INTERPOLATION OPERATOR; THEORY VALIDATION; UNIVARIATE ANALYSIS; ALGORITHM;

ALGORITHMS; MULTIVARIATE ANALYSIS; NEURAL NETWORKS (COMPUTER);

EID: 84977562383     PISSN: 08936080     EISSN: 18792782     Source Type: Journal    
DOI: 10.1016/j.neunet.2016.06.002     Document Type: Article

References (43)

1. Anastassiou, G.A., Rate of convergence of some neural network operators to the unit-univariate case. Journal of Mathematical Analysis and Applications 212 (1997), 237–262.
2. Anastassiou, G.A., Intelligent systems: Approximation by artificial neural networks Intelligent systems reference library, Vol. 19, 2011, Springer-Verlag, Berlin.
3. Anastassiou, G.A., Coroianu, L., Gal, S.G., Approximation by a nonlinear Cardaliaguet-Euvrard neural network operator of max-product kind. Journal of Computational Analysis and Applications 12:2 (2010), 396–406.
4. Bardaro, C., Karsli, H., Vinti, G., On pointwise convergence of linear integral operators with homogeneous kernels. Integral Transforms and Special Functions 19:6 (2008), 429–439.
5. Bardaro, C., Musielak, J., & Vinti, G. (2003). Nonlinear integral operators and applications, New York, Berlin, De gruyter series in nonlinear analysis and applications, Vol. 9.
6. Barron, A.R., Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transaction on Information Theory 39:3 (1993), 930–945.
7. Buhmann, M.D., Dyn, N., Levin, D., On quasi-interpolation by radial basis functions with scattered centres. Constructive Approximation 11:2 (1995), 239–254.
8. Cao, F., Chen, Z., The approximation operators with sigmoidal functions. Computers & Mathematics with Applications 58:4 (2009), 758–765.
9. Cao, F., Chen, Z., The construction and approximation of a class of neural networks operators with ramp functions. Journal of Computational Analysis and Applications 14:1 (2012), 101–112.
10. Cardaliaguet, P., Euvrard, G., Approximation of a function and its derivative with a neural network. Neural Networks 5:2 (1992), 207–220.
11. Cheang, G.H.L., Approximation with neural networks activated by ramp sigmoids. Journal of Approximation Theory 162 (2010), 1450–1465.
12. Cheney, E.W., Light, W.A., Xu, Y., Constructive methods of approximation by rigde functions and radial functions. Numerical Algorithms 4:2 (1993), 205–223.
13. Chui, C.K., Diamond, H., A natural formulation of quasi-interpolation by multivariate splines. Proceedings of the American Mathematical Society 99:4 (1987), 643–646.
14. Cluni, F., Costarelli, D., Minotti, A.M., Vinti, G., Enhancement of thermographic images as tool for structural analysis in earthquake engineering. NDT & E International 70 (2015), 60–72.
15. Coroianu, L., Gal, S.G., Approximation by nonlinear generalized sampling operators of max-product kind. Sampling Theory in Signal and Image Processing 9:1–3 (2010), 59–75.
16. Coroianu, L., Gal, S.G., Approximation by max-product sampling operators based on sinc-type kernels. Sampling Theory in Signal and Image Processing 10:3 (2011), 211–230.
17. Coroianu, L., Gal, S.G., Saturation results for the truncated max-product sampling operators based on sinc and Fejér-type kernels. Sampling Theory in Signal and Image Processing 11:1 (2012), 113–132.
18. Coroianu, L., Gal, S.G., Saturation and inverse results for the Bernstein max-product operator. Periodica Mathematica Hungarica 69 (2014), 126–133.
19. Costarelli, D., Neural network operators: constructive interpolation of multivariate functions. Neural Networks 67 (2015), 28–36.
20. Costarelli, D., Spigler, R., Multivariate neural network operators with sigmoidal activation functions. Neural Networks 48 (2013), 72–77.
21. Costarelli, D., Spigler, R., Convergence of a family of neural network operators of the Kantorovich type. Journal of Approximation Theory 185 (2014), 80–90.
22. Costarelli, D., Spigler, R., Approximation by series of sigmoidal functions with applications to neural networks. Annali di Matematica Pura ed Applicata 194:1 (2015), 289–306.
23. Costarelli, D., Vinti, G., Order of approximation for sampling Kantorovich operators. Journal of Integral Equations and Applications 26:3 (2014), 345–368.
24. Costarelli, D., Vinti, G., Rate of approximation for multivariate sampling Kantorovich operators on some functions spaces. Journal of Integral Equations and Applications 26:4 (2014), 455–481.
25. Costarelli, D., Vinti, G., Degree of approximation for nonlinear multivariate sampling Kantorovich operators on some functions spaces. Numerical Functional Analysis and Optimization 36:8 (2015), 964–990.
26. Costarelli, D., Vinti, G., Max-product neural network and quasi interpolation operators activated by sigmoidal functions. Journal of Approximation Theory 209 (2016), 1–22.
27. Cybenko, G., Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems 2 (1989), 303–314.
28. Di Marco, M., Forti, M., Grazzini, M., Pancioni, L., Necessary and sufficient condition for multistability of neural networks evolving on a closed hypercube. Neural Networks 54 (2014), 38–48.
29. Di Marco, M., Forti, M., Nistri, P., Pancioni, L., Discontinuous neural networks for finite-time solution of time-dependent linear equations. IEEE Transactions on Cybernetics PP:99 (2015), 1–12, 10.1109/TCYB.2015.2479118.
30. Fang, Q., Wang, R.H., Xu, M., A kind of improved univariate multiquadric quasi-interpolation operators. Computers & Mathematics with Applications 59:1 (2010), 451–456.
31. Gnecco, G., Sanguineti, M., On a variational norm tailored to variable-basis approximation schemes. IEEE Transaction on Information Theory 57 (2011), 549–558.
32. Gripenberg, G., Approximation by neural network with a bounded number of nodes at each level. Journal of Approximation Theory 122:2 (2003), 260–266.
33. Iliev, A.I., Kyurkchiev, N., Markov, S., On the approximation of the cut and step functions by logistic and Gompertz functions. BIOMATH, 4(2), 2015 Article-ID 1510101.
34. Ismailov, V.E., On the approximation by neural networks with bounded number of neurons in hidden layers. Journal of Mathematical Analysis and Applications 417:2 (2014), 963–969.
35. Ito, Y., Independence of unscaled basis functions and finite mappings by neural networks. Mathematical Sciences 26 (2001), 117–126.
36. Kainen, P.C., Kurková, V., An integral upper bound for neural network approximation. Neural Computation 21 (2009), 2970–2989.
37. Li, C.J., Wang, R.H., Bivariate quartic spline spaces and quasi-interpolation operators. Journal of Computational and Applied Mathematics 190:1 (2006), 325–338.
38. Llanas, B., Sainz, F.J., Constructive approximate interpolation by neural networks. Journal of Computational and Applied Mathematics 188 (2006), 283–308.
39. Maiorov, V., Approximation by neural networks and learning theory. Journal of Complexity 22:1 (2006), 102–117.
40. Makovoz, Y., Uniform approximation by neural networks. Journal of Approximation Theory 95:2 (1998), 215–228.
41. Schaback, R., Wu, Z., Construction techniques for highly accurate quasi-interpolation operators. Journal of Approximation Theory 91:3 (1997), 320–331.
42. Sontag, E.D., Feedforward nets for interpolation and classification. Journal of Computer and System Sciences 45 (1992), 20–48.
43. Verfurth, R., Error estimates for some quasi-interpolation operators. ESAIM: Mathematical Modelling and Numerical Analysis 33:4 (1999), 695–713.