Quantitative estimates involving K-functionals for neural network-type operators

References

• Cao F , Chen Z . Scattered data approximation by neural networks operators. Neurocomputing. 2016;190:237–242.
   Web of Science ®Google Scholar
• Fard SP , Zainuddin Z . The universal approximation capabilities of cylindrical approximate identity neural networks. Arabian J Sci Eng. 2016;1–8.
   Web of Science ®Google Scholar
• Fard SP , Zainuddin Z . Theoretical analyses of the universal approximation capability of a class of higher order neural networks based on approximate identity. Nat-inspired Comput: Concepts, Methodologies Tools Appl. Forthcoming 2016. DOI:10.4018/978-1-5225-0788-8.ch055.
   Google Scholar
• Costarelli D , Vinti G . Voronovskaja formulas for high order convergence neural network operators with sigmoidal functions. 2017. submitted for publication.
   Google Scholar
• Costarelli D , Spigler R . Convergence of a family of neural network operators of the Kantorovich type. J Approx Theory. 2014;185:80–90.
   Web of Science ®Google Scholar
• Costarelli D , Vinti G . Convergence for a family of neural network operators in Orlicz spaces. Mathematische Nachrichten. 2017;290(2–3):226–235.
   Web of Science ®Google Scholar
• Costarelli D , Vinti G . Approximation by max-product neural network operators of Kantorovich type. Results Math. 2016;69(3):505–519.
   Web of Science ®Google Scholar
• Costarelli D . Neural network operators: constructive interpolation of multivariate functions. Neural Networks. 2015;67:28–36.
   PubMed Web of Science ®Google Scholar
• Burger M , Neubauer A . Error bounds for approximation with neural networks. J Approximation Theory. 2001;112(2):235–250.
   Web of Science ®Google Scholar
• Gripenberg G . Approximation by neural network with a bounded number of nodes at each level. J Approx Theory. 2003;122(2):260–266.
   Web of Science ®Google Scholar
• Kainen PC , Kurková V . An integral upper bound for neural network approximation. Neural Comput. 2009;21:2970–2989.
   PubMed Web of Science ®Google Scholar
• Alexandridis AK , Zapranis AD . Wavelet neural networks: A practical guide. Neural Networks. 2013;42:1–27.
   PubMed Web of Science ®Google Scholar
• 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. 2014;54:38–48.
   PubMed Web of Science ®Google Scholar
• Di Marco M , Forti M , Nistri P , Pancioni L . Discontinuous neural networks for finite-time solution of time-dependent linear equations. IEEE Trans Cybern. 2015;99:1–12. DOI:10.1109/TCYB.2015.2479118.
   Google Scholar
• Austin J , Hodge VJ , O’Keefe S . Hadoop neural network for parallel and distributed feature selection. Neural Networks. 2016;78:24–35.
   PubMed Web of Science ®Google Scholar
• Jia F , Lei Y , Lin J , Lu N . X., Zhou, Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech Syst Signal Process. 2016;72:303–315.
   Web of Science ®Google Scholar
• Shi Z , Wu Y , Ye Y . Rank-based pooling for deep convolutional neural networks. Neural Networks. 2016;83:21–31.
   PubMed Web of Science ®Google Scholar
• Liu P , Wang J , Zeng Z . Multistability of delayed recurrent neural networks with Mexican hat activation functions. Neural Comput. 2017;29(2):423–457.
   PubMed Web of Science ®Google Scholar
• Cao F , Xie T , Xu Z . The estimate for approximation error of neural networks: A constructive approach. Neurocomputing. 2008;71(4):626–630.
   Web of Science ®Google Scholar
• Cao F , Zhang R . The errors of approximation for feedforward neural networks in the Lp metric. Math Comput Model. 2009;49(7):1563–1572.
   Google Scholar
• Peetre J . A new approach in interpolation spaces. Studia Math. 1970;34:23–42.
   Web of Science ®Google Scholar
• Peetre J , Sparr G . Interpolation of normed Abelian group. Annali di Matematica Pura ed Applicata. 1972;92:217–262.
   Google Scholar
• DeVore RA , Lorentz GG . Constructive approximation. Vol. 303, Berlin: Springer Science & Business Media.
   Google Scholar
• Berens H , Butzer PL . Semigroups of operators and approximation. New York: Springer-Verlag; 1967.
   Google Scholar
• Maiorov V , Meir R . On the near optimality of the stochastic approximation of smooth functions by neural networks. Adv Comput Math. 2000;13(1):79–103.
   Web of Science ®Google Scholar
• Maiorov V . Approximation by neural networks and learning theory. J Complexity. 2006;22(1):102–117.
   Web of Science ®Google Scholar
• Cao F , Xu Z . The essential order of approximation for neural networks. Sci China Ser F: Inf Sci. 2004;47(1):97–112.
   Google Scholar
• Cao F , Xu Z . Simultaneous Lp -approximation order for neural networks. Neural Networks. 2005;18(7):914–923.
   PubMed Web of Science ®Google Scholar
• Barron AR , Klusowski JM . Uniform approximation by neural networks activated by first and second order ridge splines. 2016. arXiv preprint arXiv:1607.07819.
   Google Scholar
• Chui CK , Mhaskar HN . Deep nets for local manifold learning. 2016. arXiv preprint arXiv:1607.07110.
   Google Scholar
• Lin S , Zeng J , Zhang X . Constructive neural network learning. 2016. arXiv preprint arXiv:1605.00079.
   Google Scholar
• Mhaskar H , Poggio T . Deep vs. shallow networks: an approximation theory perspective. Anal Appl. 2016;14(6):829–848.
   Google Scholar
• Schmidhuber J . Deep learning in neural networks: An overview. Neural Networks. 2015;61:85–117.
   PubMed Web of Science ®Google Scholar
• Cao F , Chen Z . The approximation operators with sigmoidal functions. Comput Math Appl. 2009;58(4):758–765.
   Web of Science ®Google Scholar
• Costarelli D , Vinti G . Max-product neural network and quasi interpolation operators activated by sigmoidal functions. J Approx Theory. 2016;209:1–22.
   Web of Science ®Google Scholar
• Costarelli D , Vinti G . Pointwise and uniform approximation by multivariate neural network operators of the max-product type. Neural Networks. 2016;81:81–90.
   PubMed Web of Science ®Google Scholar
• Costarelli D , Vinti G . Saturation classes for max-product neural network operators activated by sigmoidal functions. Results Math. 2017;72(3):1555–1569.
   Web of Science ®Google Scholar
• Coroianu L , Gal SG . Lp - approximation by truncated max-product sampling operators of Kantorovich-type based on Fejer kernel. J Integral Equ Appl. 2017;29(2):349–364.
   Web of Science ®Google Scholar
• Costarelli D , Spigler R . A collocation method for solving nonlinear Volterra integro-differential equations of the neutral type by sigmoidal functions. J Integral Equ Appl. 2014;26(1):15–52.
   Web of Science ®Google Scholar
• Costarelli D , Spigler R . Solving Volterra integral equations of the second kind by sigmoidal functions approximation. J Integral Equ Appl. 2013;25(2):193–222.
   Web of Science ®Google Scholar
• Hahm N , Hong BI . A Note on neural network approximation with a sigmoidal function. Appl Math Sci. 2016;10(42):2075–2085.
   Google Scholar
• Iliev A , Kyurkchiev N . On the Hausdorff distance between the Heaviside function and some transmuted activation functions. Mathematical Modeling and Applications. 2016;2(1):1–5.
   Google Scholar
• Iliev A , Kyurkchiev N , Markov S . On the approximation of the cut and step functions by logistic and Gompertz functions. BIOMATH. 2015;4(2):1510101.
   Google Scholar
• Kurková V . Lower bounds on complexity of shallow perceptron networks. Eng Appl Neural Networks Commun Comput Inf Sci. 2016;629:283–294.
   Google Scholar
• Scardapane S , Wang D . Randomness in Neural Network: an overview. Wiley interdisciplinary reviews: data mining and knowledge discovery. 2017;7:e 1200. DOI:10.1002/widm.1200.
   Web of Science ®Google Scholar
• Baldi P , Sadowsky P . A theory of local learning, the learning channel, and the optimality of backpropagation. Neural Networks. 2016;83:51–74.
   PubMed Web of Science ®Google Scholar
• Cheang GHL . Approximation with neural networks activated by ramp sigmoids. J Approx Theory. 2010;162:1450–1465.
   Web of Science ®Google Scholar
• Bardaro C , Karsli H , Vinti G . Nonlinear integral operators with homogeneous kernels: pointwise approximation theorems. Appl Anal. 2011;90(3–4):463–474.
   Web of Science ®Google Scholar
• Angeloni L , Vinti G . Approximation in variation by homothetic operators in multidimensional setting. Differ Int Equ. 2013;26(5–6):655–674.
   Google Scholar
• Costarelli D , Vinti G . Rate of approximation for multivariate sampling Kantorovich operators on some functions spaces. J Int Equ Appl. 2014;26(4):455–481.
   Web of Science ®Google Scholar
• Vinti G , Zampogni L . Approximation results for a general class of Kantorovich type operators. Adv Nonlinear Stud. 2014;14:991–1011.
   Web of Science ®Google Scholar
• Costarelli D , Vinti G . Degree of approximation for nonlinear multivariate sampling Kantorovich operators on some functions spaces. Numer Funct Anal Optim. 2015;36(8):964–990.
   Web of Science ®Google Scholar
• Cluni F , Costarelli D , Minotti AM , et al . Applications of sampling Kantorovich operators to thermographic images for seismic engineering. J Comput Anal Appl. 2015;19(4):602–617.
   Web of Science ®Google Scholar
• Costarelli D , Minotti AM , Vinti G . Approximation of discontinuous signals by sampling Kantorovich series. J Math Anal Appl. 2017;450(2):1083–1103.
   Web of Science ®Google Scholar