Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces. (English) Zbl 1402.41006
Summary: In this paper, we study the theory of a Kantorovich version of the multivariate neural network operators. Such operators, are activated by suitable kernels generated by sigmoidal functions. In particular, the main result here proved is a modular convergence theorem in Orlicz spaces. As special cases, convergence theorem in \(L^p\)-spaces, interpolation spaces, and exponential-type spaces can be deduced. In general, multivariate approximations by constructive neural network algorithms are useful for applications to neurocomputing processes involving high dimensional data. At the end of the paper, several examples of activation functions of sigmoidal-type for which the above theory holds have been described.
MSC:
| 41A30 | Approximation by other special function classes |
| 41A25 | Rate of convergence, degree of approximation |
| 47A58 | Linear operator approximation theory |
References:
| [1] | Anastassiou, G.A.: Intelligent Systems: Approximation by Artificial Neural Networks. Intelligent Systems Reference Library 19. Springer, Berlin (2011) · Zbl 1243.68002 · doi:10.1007/978-3-642-21431-8 |
| [2] | Anastassiou, GA; Coroianu, L.; Gal, SG, Approximation by a nonlinear Cardaliaguet-Euvrard neural network operator of max-product kind, J. Comput. Anal. Appl., 12, 396-406, (2010) · Zbl 1232.41020 |
| [3] | Angeloni, L.; Vinti, G., Approximation with respect to Goffman-Serrin variation by means of non-convolution type integral operators, Numer. Funct. Anal. Optim., 31, 519-548, (2010) · Zbl 1200.41015 · doi:10.1080/01630563.2010.490549 |
| [4] | Angeloni, L.; Vinti, G., Approximation in variation by homothetic operators in multidimensional setting, Differ. Int. Equ., 26, 655-674, (2013) · Zbl 1299.41026 |
| [5] | Bardaro, C.; Butzer, PL; Stens, RL; Vinti, G., Kantorovich-type generalized sampling series in the setting of Orlicz spaces, Sampl. Theory Signal Image Proc., 6, 29-52, (2007) · Zbl 1156.41307 |
| [6] | Bardaro, C.; Karsli, H.; Vinti, G., On pointwise convergence of linear integral operators with homogeneous kernels, Integral Trans. Spec. Funct., 19, 429-439, (2008) · Zbl 1156.41006 · doi:10.1080/10652460801936648 |
| [7] | Bardaro, C.; Karsli, H.; Vinti, G., Nonlinear integral operators with homogeneous kernels: pointwise approximation theorems, Appl. Anal., 90, 463-474, (2011) · Zbl 1214.41006 · doi:10.1080/00036811.2010.499506 |
| [8] | Bardaro, C.; Mantellini, I., Modular approximation by sequences of nonlinear integral operators in Musielak-Orlicz spaces, Atti Sem. Mat. Fis. Univ. Modena, 46, 403-425, (1998) · Zbl 0918.46030 |
| [9] | Bardaro, C., Musielak, J., Vinti, G.: Nonlinear Integral Operators and Applications. De Gruyter Series in Nonlinear Analysis and Applications 9. New York, Berlin (2003) · Zbl 1030.47003 |
| [10] | Barron, AR, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Trans. Inform. Theory, 39, 930-945, (1993) · Zbl 0818.68126 · doi:10.1109/18.256500 |
| [11] | Boccuto, A.; Bukhvalov, AV; Sambucini, AR, Inequalities in classical spaces with mixed norms, Positivity, 6, 393-411, (2002) · Zbl 1043.46025 · doi:10.1023/A:1021353215312 |
| [12] | Boccuto, A.; Candeloro, D.; Sambucini, AR, Vitali-type theorems for filter convergence related to Riesz space-valued modulars and applications to stochastic processes, J. Math. Anal. Appl., 419, 818-838, (2014) · Zbl 1349.46044 · doi:10.1016/j.jmaa.2014.05.014 |
| [13] | Boccuto, A., Candeloro, D., Sambucini, A.R.: \(L^p\) spaces in vector lattices and applications (2016). Accepted for publication in Math. Slov., arXiv:1604.07570 · Zbl 1505.28018 |
| [14] | Candés, EJ, Harmonic analysis of neural networks, Appl. Comput. Harmon. Anal., 6, 197-218, (1999) · Zbl 0931.68104 · doi:10.1006/acha.1998.0248 |
| [15] | Cao, F.; Chen, Z., The approximation operators with sigmoidal functions, Comput. Math. Appl., 58, 758-765, (2009) · Zbl 1189.41014 · doi:10.1016/j.camwa.2009.05.001 |
| [16] | Cao, F.; Chen, Z., The construction and approximation of a class of neural networks operators with ramp functions, J. Comput. Anal. Appl., 14, 101-112, (2012) · Zbl 1269.41003 |
| [17] | Cao, F.; Chen, Z., Scattered data approximation by neural networks operators, Neurocomputing, 190, 237-242, (2016) · doi:10.1016/j.neucom.2016.01.013 |
| [18] | Cao, F.; Liu, B.; Park, DS, Image classification based on effective extreme learning machine, Neurocomputing, 102, 90-97, (2013) · doi:10.1016/j.neucom.2012.02.042 |
| [19] | Cardaliaguet, P.; Euvrard, G., Approximation of a function and its derivative with a neural network, Neural Netw., 5, 207-220, (1992) · doi:10.1016/S0893-6080(05)80020-6 |
| [20] | Cheang, GHL, Approximation with neural networks activated by ramp sigmoids, J. Approx. Theory, 162, 1450-1465, (2010) · Zbl 1203.82069 · doi:10.1016/j.jat.2010.03.004 |
| [21] | Cheney, EW; Light, WA; Xu, Y., Constructive methods of approximation by ridge functions and radial functions, Numer. Algorithms, 4, 205-223, (1993) · Zbl 0764.41017 · doi:10.1007/BF02144104 |
| [22] | Cluni, F.; Costarelli, D.; Minotti, AM; Vinti, G., Applications of sampling Kantorovich operators to thermographic images for seismic engineering, J. Comput. Anal. Appl., 19, 602-617, (2015) · Zbl 1369.94021 |
| [23] | Cluni, F.; Costarelli, D.; Minotti, AM; Vinti, G., Enhancement of thermographic images as tool for structural analysis in earthquake engineering, NDT E Int., 70, 60-72, (2015) · doi:10.1016/j.ndteint.2014.10.001 |
| [24] | Costarelli, D., Interpolation by neural network operators activated by ramp functions, J. Math. Anal. Appl., 419, 574-582, (2014) · Zbl 1298.41037 · doi:10.1016/j.jmaa.2014.05.013 |
| [25] | Costarelli, D., Neural network operators: constructive interpolation of multivariate functions, Neural Netw., 67, 28-36, (2015) · Zbl 1396.41019 · doi:10.1016/j.neunet.2015.02.002 |
| [26] | Costarelli, D.; Minotti, AM; Vinti, G., Approximation of discontinuous signals by sampling Kantorovich series, J. Math. Anal. Appl., 450, 1083-1103, (2017) · Zbl 1373.41018 · doi:10.1016/j.jmaa.2017.01.066 |
| [27] | Costarelli, D.; Spigler, R., Solving Volterra integral equations of the second kind by sigmoidal functions approximation, J. Integral Equ. Appl., 25, 193-222, (2013) · Zbl 1285.65086 · doi:10.1216/JIE-2013-25-2-193 |
| [28] | Costarelli, D.; Spigler, R., Convergence of a family of neural network operators of the Kantorovich type, J. Approx. Theory, 185, 80-90, (2014) · Zbl 1297.41003 · doi:10.1016/j.jat.2014.06.004 |
| [29] | Costarelli, D.; Spigler, R., A collocation method for solving nonlinear Volterra integro-differential equations of the neutral type by sigmoidal functions, J. Int. Equ. Appl., 26, 15-52, (2014) · Zbl 1288.65185 · doi:10.1216/JIE-2014-26-1-15 |
| [30] | Costarelli, D.; Spigler, R., Approximation by series of sigmoidal functions with applications to neural networks, Ann. Mat. Pura Appl., 194, 289-306, (2015) · Zbl 1321.41021 · doi:10.1007/s10231-013-0378-y |
| [31] | Costarelli, D.; Spigler, R., Solving numerically nonlinear systems of balance laws by multivariate sigmoidal functions approximation, Comput. Appl. Math., 37, 99-133, (2018) · Zbl 1395.65115 · doi:10.1007/s40314-016-0334-8 |
| [32] | Costarelli, D.; Vinti, G., Order of approximation for sampling Kantorovich operators, J. Int. Equ. Appl., 26, 345-368, (2014) · Zbl 1308.41016 · doi:10.1216/JIE-2014-26-3-345 |
| [33] | Costarelli, D.; Vinti, G., Rate of approximation for multivariate sampling Kantorovich operators on some functions spaces, J. Int. Equ. Appl., 26, 455-481, (2014) · Zbl 1308.41017 · doi:10.1216/JIE-2014-26-4-455 |
| [34] | Costarelli, D.; Vinti, G., Degree of approximation for nonlinear multivariate sampling Kantorovich operators on some functions spaces, Numer. Funct. Anal. Optim., 36, 964-990, (2015) · Zbl 1327.41008 · doi:10.1080/01630563.2015.1040888 |
| [35] | Costarelli, D.; Vinti, G., Approximation by max-product neural network operators of Kantorovich type, Results Math., 69, 505-519, (2016) · Zbl 1355.41009 · doi:10.1007/s00025-016-0546-7 |
| [36] | Costarelli, D.; Vinti, G., Max-product neural network and quasi interpolation operators activated by sigmoidal functions, J. Approx. Theory, 209, 1-22, (2016) · Zbl 1350.41001 · doi:10.1016/j.jat.2016.05.001 |
| [37] | Costarelli, D.; Vinti, G., Pointwise and uniform approximation by multivariate neural network operators of the max-product type, Neural Netw., 81, 81-90, (2016) · Zbl 1439.41009 · doi:10.1016/j.neunet.2016.06.002 |
| [38] | Costarelli, D.; Vinti, G., Convergence for a family of neural network operators in Orlicz spaces, Math. Nachr., 290, 226-235, (2017) · Zbl 1373.47010 · doi:10.1002/mana.201600006 |
| [39] | Costarelli, D.; Vinti, G., Saturation classes for max-product neural network operators activated by sigmoidal functions, Results Math., 72, 1555-1569, (2017) · Zbl 1376.41014 · doi:10.1007/s00025-017-0692-6 |
| [40] | Cybenko, G., Approximation by superpositions of a sigmoidal function, Math. Control Signals Syst., 2, 303-314, (1989) · Zbl 0679.94019 · doi:10.1007/BF02551274 |
| [41] | 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) · Zbl 1322.93011 · doi:10.1016/j.neunet.2014.02.010 |
| [42] | Marco, M.; Forti, M.; Nistri, P.; Pancioni, L., Discontinuous neural networks for finite-time solution of time-dependent linear equations, IEEE Trans. Cybern., 46, 2509-2520, (2016) · doi:10.1109/TCYB.2015.2479118 |
| [43] | Girosi, F.; Poggio, T., Networks and best approximation property, Biol. Cybern., 63, 169-176, (1990) · Zbl 0714.94029 · doi:10.1007/BF00195855 |
| [44] | Gripenberg, G., Approximation by neural network with a bounded number of nodes at each level, J. Approx. Theory, 122, 260-266, (2003) · Zbl 1019.41018 · doi:10.1016/S0021-9045(03)00078-9 |
| [45] | Ismailov, VE, On the approximation by neural networks with bounded number of neurons in hidden layers, J. Math. Anal. Appl., 417, 963-969, (2014) · Zbl 1303.41010 · doi:10.1016/j.jmaa.2014.03.092 |
| [46] | Ito, Y., Independence of unscaled basis functions and finite mappings by neural networks, Math. Sci., 26, 117-126, (2001) · Zbl 1052.68010 |
| [47] | Kainen, PC; Kurková, V., An integral upper bound for neural network approximation, Neural Comput., 21, 2970-2989, (2009) · Zbl 1186.68370 · doi:10.1162/neco.2009.04-08-745 |
| [48] | Kurková, V.; Sanguineti, M., Model complexities of shallow networks representing highly varying functions, Neurocomputing, 171, 598-604, (2016) · doi:10.1016/j.neucom.2015.07.014 |
| [49] | Kyurkchiev, N., Markov, S.: Sigmoid functions: some approximation and modeling aspects. Some Moduli in Programming Environment Mathematica, LAP (Lambert Acad. Publ.) (2015) · Zbl 1387.41009 |
| [50] | Lin, S.; Xu, Z.; Zeng, J., Error estimate for spherical neural networks interpolation, Neural Process. Lett., 42, 369-379, (2015) · doi:10.1007/s11063-014-9361-x |
| [51] | Llanas, B.; Sainz, FJ, Constructive approximate interpolation by neural networks, J. Comput. Appl. Math., 188, 283-308, (2006) · Zbl 1089.65012 · doi:10.1016/j.cam.2005.04.019 |
| [52] | Maiorov, V., Approximation by neural networks and learning theory, J. Complex., 22, 102-117, (2006) · Zbl 1156.68541 · doi:10.1016/j.jco.2005.09.001 |
| [53] | Makovoz, Y., Uniform approximation by neural networks, J. Approx. Theory, 95, 215-228, (1998) · Zbl 0932.41016 · doi:10.1006/jath.1997.3217 |
| [54] | Musielak, J.: Orlicz Spaces and Modular Spaces. Lecture Notes in Math, vol. 1034. Springer, Berlin (1983) · Zbl 0557.46020 · doi:10.1007/BFb0072210 |
| [55] | Musielak, J.; Orlicz, W., On modular spaces, Studia Math., 28, 49-65, (1959) · Zbl 0086.08901 · doi:10.4064/sm-18-1-49-65 |
| [56] | Rao, M.M., Ren, Z.D.: Theory of Orlicz Spaces. Pure and Applied Mathematics. Marcel Dekker Inc., New York (1991) · Zbl 0724.46032 |
| [57] | Rao, M.M., Ren, Z.D.: Applications of Orlicz Spaces. Monographs and Textbooks in Pure and Applied Mathematics, vol. 250. Marcel Dekker Inc., New York (2002) · Zbl 0997.46027 |
| [58] | Vinti, G.; Zampogni, L., Approximation results for a general class of Kantorovich type operators, Adv. Nonlinear Stud., 14, 991-1011, (2014) · Zbl 1305.41027 · doi:10.1515/ans-2014-0410 |
| [59] | Vinti, G., Zampogni, L.: A general approximation approach for the simultaneous treatment of integral and discrete operators. Adv. Nonlinear Stud. (2017). https://doi.org/10.1515/ans-2017-6038. arXiv:1711.09230 · Zbl 1403.41005 |
| [60] | Wu, ZB; Cao, F., Simultaneous \(L^p\) approximation order for neural networks, Neural Netw., 18, 914-923, (2005) · Zbl 1088.68158 · doi:10.1016/j.neunet.2005.03.013 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
