Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions

References

• Chen, T., Chen, H. (1993). Approximation of continuous functionals by neural networks with application to dynamic systems. IEEE Trans. Neural Netw. 4(6):910–918. DOI: 10.1109/72.286886.
   PubMedGoogle Scholar
• Chui, C. K., Li, X. (1992). Approximation by ridge functions and neural networks with one hidden layer. J. Approx. Theory 70(2):131–141. DOI: 10.1016/0021-9045(92)90081-X.
   Web of Science ®Google Scholar
• Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Math. Control. Signal. Syst. 2(4):303–314. DOI: 10.1007/BF02551274.
   Google Scholar
• Hornik, K. (1991). Approximation capabilities of multilayer feedforward networks. Neural Netw. 4(2):251–257. DOI: 10.1016/0893-6080(91)90009-T.
   Web of Science ®Google Scholar
• Ito, Y. (1992). Approximation of continuous functions on Rd by linear combinations of shifted rotations of a sigmoid function with and without scaling. Neural Netw. Networks 5:105–115. DOI: 10.1016/S0893-6080(05)80009-7.
   Web of Science ®Google Scholar
• Leshno, M., Lin, V. Ya., Pinkus, A., Schocken, S. (1993). Multilayer feedforward networks with a non-polynomial activation function can approximate any function. Neural Netw. 6(6):861–867. DOI: 10.1016/S0893-6080(05)80131-5.
   Web of Science ®Google Scholar
• Costarelli, D., Vinti, G. (2017). Convergence for a family of neural network operators in Orlicz spaces. Math. Nachr. 290(2–3):226–235. DOI: 10.1002/mana.201600006.
   Web of Science ®Google Scholar
• Costarelli, D., Vinti, G. (2017). Saturation classes for max-product neural network operators activated by sigmoidal functions. Results Math. 72(3):1555–1569. DOI: 10.1007/s00025-017-0692-6.
   Web of Science ®Google Scholar
• Guliyev, N. J., Ismailov, V. E. (2016). A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function. Neural Comput. 28(7):1289–1304. DOI: 10.1162/NECO_a_00849.
   PubMed Web of Science ®Google Scholar
• Guliyev, N. J., Ismailov, V. E. (2018). On the approximation by single hidden layer feedforward neural networks with fixed weights. Neural Netw. 98:296–304. DOI: 10.1016/j.neunet.2017.12.007.
   PubMed Web of Science ®Google Scholar
• Petrushev, P. P. (1998). Approximation by ridge functions and neural networks. SIAM J. Math. Anal. 30(1):155–189. DOI: 10.1137/S0036141097322959.
   Web of Science ®Google Scholar
• Pinkus, A. (1999). Approximation theory of the MLP model in neural networks. Acta Numer. 8:143–195. DOI: 10.1017/S0962492900002919.
   Google Scholar
• Stinchcombe, M., White, H. (1990). Approximating and learning unknown mappings using multilayer feedforward networks with bounded weights, in Proceedings of the IEEE 1990 International Joint Conference on Neural Networks, Vol. 3, IEEE, New York, 7–16.
   Google Scholar
• Ismailov, V. E. (2015). Approximation by ridge functions and neural networks with a bounded number of neurons. Appl. Anal. 94(11):2245–2260. DOI: 10.1080/00036811.2014.979809.
   Web of Science ®Google Scholar
• Ismailov, V. E. (2012). Approximation by neural networks with weights varying on a finite set of directions. J. Math. Anal. Appl. 389(1):72–83. DOI: 10.1016/j.jmaa.2011.11.037.
   Web of Science ®Google Scholar
• Ismailov, V. E., Savas, E. (2017). Measure theoretic results for approximation by neural networks with limited weights. Numer. Funct. Anal. Optim. 38(7):819–830. DOI: 10.1080/01630563.2016.1254654.
   Web of Science ®Google Scholar
• Barron, A. R. (1993). Universal approximation bounds for superposition of a sigmoidal function. IEEE Trans. Inform. Theory 39(3):930–945. DOI: 10.1109/18.256500.
   Web of Science ®Google Scholar
• Hahm, N., Hong, B. I. (1999). Extension of localized approximation by neural networks. BAZ 59(1):121–131. DOI: 10.1017/S0004972700032676.
   Google Scholar
• Lin, S., Guo, X., Cao, F., Xu, Z. (2013). Approximation by neural networks with scattered data. Appl. Math. Comput. 224:29–35. DOI: 10.1016/j.amc.2013.08.014.
   Web of Science ®Google Scholar
• Lin, S., Zeng, J., Xu, L., Xu, Z. (2015). Jackson-type inequalities for spherical neural networks with doubling weights. Neural Netw. 63:57–65. DOI: 10.1016/j.neunet.2014.11.002.
   PubMed Web of Science ®Google Scholar
• Maiorov, V., Meir, R. S. (1998). Approximation bounds for smooth functions in C(Rd) by neural and mixture networks. IEEE Trans. Neural Netw. 9:969–978. DOI: 10.1109/72.712173.
   PubMedGoogle Scholar
• Mhaskar, H. N., Micchelli, C. A. (1995). Degree of approximation by neural networks with a single hidden layer. Adv. Appl. Math. 16(2):151–183. DOI: 10.1006/aama.1995.1008.
   Web of Science ®Google Scholar
• Braess, D., Pinkus, A. (1993). Interpolation by ridge functions. J. Approx. Theory 73(2):218–236. DOI: 10.1006/jath.1993.1039.
   Web of Science ®Google Scholar
• Ismailov, V. E., Pinkus, A. (2013). Interpolation on lines by ridge functions. J. Approx. Theory 175:91–113. DOI: 10.1016/j.jat.2013.07.010.
   Web of Science ®Google Scholar
• Arnold, V.I. On functions of three variables, Dokl. Akad. Nauk SSSR 114 (1957): 679–681; English transl, Am. Math. Soc. Transl. 28 (1963): 51–54.
   Google Scholar
• Ismailov, V. E. (2006). On error formulas for approximation by sums of univariate functions. Int. J. Math. Sci. 2006: Article ID 65620, 11 pp. DOI: 10.1155/IJMMS/2006/65620.
   Google Scholar
• Ismailov, V. E. (2006). Methods for computing the least deviation from the sums of functions of one variable, (Russian). Sibirskii Mat. Zhurnal 47:1076–1082; translation in Siberian Math. J. 47:883–888. DOI: 10.1007/s11202-006-0097-3.
   Google Scholar
• Khavinson, S. Y. (1997). Best Approximation by Linear Superpositions (Approximate Nomography). Translated from the Russian manuscript by D. Khavinson. Translations of Mathematical Monographs, 159. American Mathematical Society, Providence, RI, 175 pp.
   Google Scholar
• Marshall, D. E., O'Farrell, A. G. (1983). Approximation by a sum of two algebras. The lightning bolt principle. J. Funct. Anal. 52(3):353–368. DOI: 10.1016/0022-1236(83)90074-5.
   Web of Science ®Google Scholar
• Diliberto, S. P., Straus, E. G. (1951). On the approximation of a function of several variables by the sum of functions of fewer variables. Pacific J. Math. 1(2):195–210. DOI: 10.2140/pjm.1951.1.195.
   Google Scholar
• Golitschek, M. V., Light, W. A. (1992). Approximation by solutions of the planar wave equation. SIAM J. Numer. Anal. 29:816–830. DOI: 10.1137/0729050.
   Web of Science ®Google Scholar
• Marshall, D., O'Farrell, A. (1979). Uniform approximation by real functions. Fund. Math. 104(3):203–211. DOI: 10.4064/fm-104-3-203-211.
   Google Scholar
• Ismailov, V. E. (2012). A note on the representation of continuous functions by linear superpositions. Expo. Math. 30(1):96–101. DOI: 10.1016/j.exmath.2011.07.005.
   Web of Science ®Google Scholar
• Ismailov, V. E. (2008). On the representation by linear superpositions. J. Approx. Theory 151(2):113–125. DOI: 10.1016/j.jat.2007.09.003.
   Web of Science ®Google Scholar
• Logan, B. F., Shepp, L. A. (1975). Optimal reconstruction of a function from its projections. Duke Math. J. 42(4):645–659. DOI: 10.1215/S0012-7094-75-04256-8.
   Web of Science ®Google Scholar
• Natterer, F. (1986). The Mathematics of Computerized Tomography. New York: Wiley.
   Google Scholar
• Candés, E. J. (2003). Ridgelets: estimating with ridge functions. Ann. Stat. 31:1561–1599. DOI: 10.1214/aos/1065705119.
   Web of Science ®Google Scholar
• Friedman, J. H., Stuetzle, W. (1981). Projection pursuit regression. J. Am. Stat. Assoc. 76(376):817–823. DOI: 10.1080/01621459.1981.10477729.
   Web of Science ®Google Scholar
• John, F. (1955). Plane Waves and Spherical Means Applied to Partial Differential Equations. New York: Interscience.
   Google Scholar
• Maiorov, V., Pinkus, A. (1999). Lower bounds for approximation by MLP neural networks. Neurocomputing 25(1–3):81–91. DOI: 10.1016/S0925-2312(98)00111-8.
   Web of Science ®Google Scholar
• Pinkus, A. (2015). Ridge Functions, Cambridge Tracts in Mathematics, Vol. 205. Cambridge: Cambridge University Press, 218 pp.
   Google Scholar
• Ismailov, V. E. (2009). On the proximinality of ridge functions. Sarajevo J. Math. 5(1):109–118.
   Google Scholar
• Ismailov, V. E. (2007). Characterization of an extremal sum of ridge functions. J. Comput. Appl. Math. 205(1):105–115. DOI: 10.1016/j.cam.2006.04.043.
   Web of Science ®Google Scholar
• Singer, I. (1974). The theory of best approximation and functional analysis. Conference Board of the Mathematical Sciences Regional Conference Series in Applied Mathematics, No. 13. Society for Industrial and Applied Mathematics, Philadelphia, PA., 95 pp.
   Google Scholar