Abstract
In the present paper, asymptotic expansion and Voronovskaja type theorem for the neural network operators have been proved. The above results are based on the computation of the algebraic truncated moments of the density functions generated by suitable sigmoidal functions, such as the logistic functions, sigmoidal functions generated by splines and other. Further, operators with high-order convergence are also studied by considering finite linear combination of the above neural network type operators and Voronovskaja type theorems are again proved. At the end of the paper, numerical results are provided.
Similar content being viewed by others
References
Alavi, J., Aminikhah, H.: Applying cubic B-Spline quasi-interpolation to solve 1D wave equations in polar coordinates. In: ISRN Computational Mathematics (2013)
Austin, J., Hodge, V.J., O’Keefe, S.: Hadoop neural network for parallel and distributed feature selection. Neural Netw. 78, 24–35 (2016)
Baldi, P., Sadowsky, P.: A theory of local learning, the learning channel, and the optimality of backpropagation. Neural Netw. 83, 51–74 (2016)
Bardaro, C., Mantellini, I.: Approximation properties for linear combinations of moment type operators. Comput. Math. Appl. 62(5), 2304–2313 (2011)
Bardaro, C., Mantellini, I.: Asymptotic formulae for linear combinations of generalized sampling operators. Zeitschrift fur Anal. ihre Anwendungen 32(3), 279–298 (2013)
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inform. Theory 39(3), 930–945 (1993)
Barron, A.R., Klusowski, J.M.: Uniform approximation by neural networks activated by first and second order ridge splines (2016). arXiv:1607.07819
Butzer, P.L., Nessel, R.J.: Fourier Analysis and Approximation I. Academic Press, New York, London (1971)
Cao, F., Chen, Z.: The approximation operators with sigmoidal functions. Comput. Math. Appl. 58(4), 758–765 (2009)
Cao, F., Chen, Z.: The construction and approximation of a class of neural networks operators with ramp functions. J. Comput. Anal. Appl. 14(1), 101–112 (2012)
Cao, F., Chen, Z.: Scattered data approximation by neural networks operators. Neurocomputing 190, 237–242 (2016)
Cao, F., Liu, B., Park, D.S.: Image classification based on effective extreme learning machine. Neurocomputing 102, 90–97 (2013)
Cheang, G.H.L.: Approximation with neural networks activated by ramp sigmoids. J. Approx. Theory 162, 1450–1465 (2010)
Chui, C.K., Mhaskar, H.N.: Deep nets for local manifold learning (2016). arXiv:1607.07110
Coroianu, L., Gal, S.G.: Saturation results for the truncated max-product sampling operators based on sinc and Fejér-type kernels. Sampl. Theory Signal Image Process. 11(1), 113–132 (2012)
Costarelli, D.: Interpolation by neural network operators activated by ramp functions. J. Math. Anal. Appl. 419(1), 574–582 (2014)
Costarelli, D., Spigler, R.: Approximation results for neural network operators activated by sigmoidal functions. Neural Netw. 44, 101–106 (2013)
Costarelli, D., Spigler, R.: Approximation by series of sigmoidal functions with applications to neural networks. Ann. di Mat. 194(1), 289–306 (2015)
Costarelli, D., Vinti, G.: Rate of approximation for multivariate sampling Kantorovich operators on some functions spaces. J. Int. Equations Appl. 26(4), 455–481 (2014)
Costarelli, D., Vinti, G.: Pointwise and uniform approximation by multivariate neural network operators of the max-product type. Neural Netw. 81, 81–90 (2016)
Costarelli, D., Vinti, G.: Convergence for a family of neural network operators in Orlicz spaces. Math. Nachr. 290(2–3), 226–235 (2017)
Costarelli, D., Vinti, G.: Saturation classes for max-product neural network operators activated by sigmoidal functions. Results Math. 72(3), 1555–1569 (2017)
Costarelli, D., Vinti, G.: Estimates for the neural network operators of the max-product type with continuous and p-integrable functions. Results Math. 73(1), 12 (2018). https://doi.org/10.1007/s00025-018-0790-0
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2, 303–314 (1989)
Di Marco, M., Forti, M., Grazzini, M., Pancioni, L.: Necessary and sufficient condition for multistability of neural networks evolving on a closed hypercube. Neural Netw. 54, 38–48 (2014)
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). https://doi.org/10.1109/TCYB.2015.2479118
Fard, S.P., Zainuddin, Z.: The universal approximation capabilities of cylindrical approximate identity neural networks. Arab. J. Sci. Eng. 41, 3027 (2016)
Fard, S.P., Zainuddin, Z.: Theoretical analyses of the universal approximation capability of a class of higher order neural networks based on approximate identity. In: Nature-inspired computing: concepts, methodologies, tools, and applications (2016). https://doi.org/10.4018/978-1-5225-0788-8.ch055(in print)
Hahm, N., Hong, B.I.: A Note on neural network approximation with a sigmoidal function. Appl. Math. Sci. 10(42), 2075–2085 (2016)
Iliev, A., Kyurkchiev, N.: On the Hausdorff distance between the Heaviside function and some transmuted activation functions. Math. Model. Appl. 2(1), 1–5 (2016)
Iliev, A., Kyurkchiev, N., Markov, S.: On the approximation of the cut and step functions by logistic and Gompertz functions. Biomath 4(2), 1510101 (2015)
Ismailov, V.E.: On the approximation by neural networks with bounded number of neurons in hidden layers. J. Math. Anal. Appl. 417(2), 963–969 (2014)
Ito, Y.: Independence of unscaled basis functions and finite mappings by neural networks. Math. Sci. 26, 117–126 (2001)
Kainen, P.C., Kurková, V.: An integral upper bound for neural network approximation. Neural Comput. 21, 2970–2989 (2009)
Korovkin, P.P.: On convergence of linear positive operators in the space of continuous functions. Dokl. Akad. Nauk SSSR 90(953), 961–964 (1953)
Kurková, V.: Lower bounds on complexity of shallow perceptron networks. Eng. Appl. Neural Netw. Commun. Comput. Inf. Sci. 629, 283–294 (2016)
Lin, S., Zeng, J., Zhang, X.: Constructive neural network learning (2016). arXiv:1605.00079
Llanas, B., Sainz, F.J.: Constructive approximate interpolation by neural networks. J. Comput. Appl. Math. 188, 283–308 (2006)
Maarten, J.: Non-equispaced B-spline wavelets. Int. J. Wavelets Multiresolution Inf. Process. 14(6), 35 (2016)
Maiorov, V.: Approximation by neural networks and learning theory. J. Complex. 22(1), 102–117 (2006)
Maiorov, V., Meir, R.: On the near optimality of the stochastic approximation of smooth functions by neural networks. Adv. Comput. Math. 13(1), 79–103 (2000)
Makovoz, Y.: Uniform approximation by neural networks. J. Approx. Theory 95(2), 215–228 (1998)
Marsden, M.J.: An identity for spline functions with applications to variation-diminishing spline approximation. J. Approx. Theory 3(1), 7–49 (1970)
Mhaskar, H., Poggio, T.: Deep vs. shallow networks: an approximation theory perspective. Anal. Appl. 14(6), 829–848 (2016)
Monaghan, J.J.: Extrapolating B splines for interpolation. J. Comput. Phys. 60(2), 253–262 (1985)
Scardapane, S., Wang, D.: Randomness in neural network: an overview. In: Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 7, p. e1200 (2017). https://doi.org/10.1002/widm.1200
Schmidhuber, J.: Deep learning in neural networks: An overview. Neural Netw. 61, 85–117 (2015)
Acknowledgements
The second and the third authors are members of the Gruppo Nazionale per l’Analisi Matematica, la Probabilità e le loro Applicazioni (GNAMPA) of the Istituto Nazionale di Alta Matematica (INdAM). The second author has been partially supported within the 2019 GNAMPA-INdAM Project “Metodi di analisi reale per l’approssimazione attraverso operatori discreti e applicazioni”, while the third author within the projects: (1) Ricerca di Base 2017 dell’Università degli Studi di Perugia—“Metodi di teoria degli operatori e di Analisi Reale per problemi di approssimazione ed applicazioni” , (2) Ricerca di Base 2018 dell’Università degli Studi di Perugia—“Metodi di Teoria dell’Approssimazione, Analisi Reale, Analisi Nonlineare e loro Applicazioni”, (3) “Metodi e processi innovativi per lo sviluppo di una banca di immagini mediche per fini diagnostici” funded by the Fondazione Cassa di Risparmio di Perugia, 2018. This research has been accomplished within RITA (Research ITalian network on Approximation).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Costarelli, D., Vinti, G. Voronovskaja Type Theorems and High-Order Convergence Neural Network Operators with Sigmoidal Functions. Mediterr. J. Math. 17, 77 (2020). https://doi.org/10.1007/s00009-020-01513-7
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s00009-020-01513-7