Approximation by ridge functions and neural networks with a bounded number of neurons

References

• Draghici S. On the capabilities of neural networks using limited precision weights. Neural Netw. 2002;15:395–414.
   PubMed Web of Science ®Google Scholar
• Ismailov VE. Approximation by neural networks with weights varying on a finite set of directions. J. Math. Anal. Appl. 2012;389:72–83.
   Web of Science ®Google Scholar
• Jian B, LiangJie Z, Yi Y. Analysis on complexity of neural networks using integer weights. Appl. Math. Inform. Sci. 2012;6:317–323.
   Web of Science ®Google Scholar
• Liao Yi, Fang S-C, Nuttle HLW. A neural network model with bounded-weights for pattern classification. Comput. OR. 2004;31:1411–1426.
   Web of Science ®Google Scholar
• Jimenez G, Ruz-Hernandez JA, Salazar-Mendoza R. Obtaining an optimal gas injection rate for an oil production system via neural networks. In: Proceedings of IEEE International Joint Conference on Neural Networks (IJCNN). Hong Kong; 2008. p. 3358–3365.
   Google Scholar
• Ruz-Hernandez JA, Salazar-Mendoza R, Jimenez G, Garcia-Hernandez R, Shelomov E. An approach based on neural networks for gas lift optimization. Stud. Comput. Intell. 2010;312:207–224.
   Google Scholar
• Jreou GNS. Application of neural network to optimize oil field production. Asian Trans. Eng. 2012;2:10–23.
   Google Scholar
• Mohaghegh S. Building the foundation for Prudhoe Bay oil production optimization using neural networks. Int. J. Oil Gas Coal Tech. 2008;1:65–80.
   Web of Science ®Google Scholar
• Chen T, Chen H. Approximation of continuous functionals by neural networks with application to dynamic systems. IEEE Trans. Neural Netw. 1993;4:910–918.
   PubMed Web of Science ®Google Scholar
• Chui CK, Li X. Approximation by ridge functions and neural networks with one hidden layer. J. Approx. Theory. 1992;70:131–141.
   Web of Science ®Google Scholar
• Cybenko G. Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 1989;2:303–314.
   Google Scholar
• Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Netw. 1991;4:251–257.
   Web of Science ®Google Scholar
• Ito Y. Approximation of continuous functions on ℝd by linear combinations of shifted rotations of a sigmoid function with and without scaling. Neural Netw. 1992;5:105–115.
   Web of Science ®Google Scholar
• Leshno M, Lin VYa, Pinkus A, Schocken S. Multilayer feedforward networks with a non-polynomial activation function can approximate any function. Neural Netw. 1993;6:861–867.
   Web of Science ®Google Scholar
• Pinkus A. Approximation theory of the MLP model in neural networks. Acta Numerica. 1999;8:143–195.
   Google Scholar
• Stinchcombe M, White H. 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. New York (NY): IEEE; 1990. p. 7–16.
   Google Scholar
• Maiorov VE. On best approximation by ridge functions. J. Approx. Theory. 1999;99:68–94.
   Web of Science ®Google Scholar
• Pinkus A. Approximating by ridge functions. In: Le Méhauté A, Rabut C, Schumaker LL, editors. Surface fitting and multiresolution methods. Nashville: Vanderbilt University Press; 1997. p. 279–292.
   Google Scholar
• Sanguineti M. Universal approximation by ridge computational models and neural networks: a survey. Open Appl. Math. J. 2008;2:31–58.
   Google Scholar
• John F. Plane waves and spherical means applied to partial differential equations. New York (NY): Interscience; 1955.
   Google Scholar
• Logan BF, Shepp LA. Optimal reconstruction of a function from its projections. Duke Math. J. 1975;42:645–659.
   Web of Science ®Google Scholar
• Kazantsev I. Tomographic reconstruction from arbitrary directions using ridge functions. Inverse Probl. 1998;14:635–645.
   Web of Science ®Google Scholar
• Marr RB. On the reconstruction of a function on a circular domain from a sampling of its line integrals. J. Math. Anal. Appl. 1974;45:357–374.
   Web of Science ®Google Scholar
• Braess D, Pinkus A. Interpolation by ridge functions. J. Approx. Theory. 1993;73:218–236.
   Web of Science ®Google Scholar
• Ismailov VE. On the representation by linear superpositions. J. Approx. Theory. 2008;151:113-125.
   Web of Science ®Google Scholar
• Klopotowski A, Nadkarni MG, Bhaskara Rao KPS. When is f(x1, x2, . , xn) = u1(x1)+u2(x2)+…+un(xn)? Proc. Indian Acad. Sci. Math. Sci. 2003;113:77–86.
   Web of Science ®Google Scholar
• Ismailov VE. On the theorem of M Golomb. Proc. Indian Acad. Sci. Math. Sci. 2009;119:45–52.
   Web of Science ®Google Scholar
• Navada KG. Some remarks on good sets. Proc. Indian Acad. Sci. Math. Sci. 2003;114:389–397.
   Web of Science ®Google Scholar
• Khavinson SYa. Best approximation by linear superpositions (approximate nomography), Translated from the Russian manuscript by D. Khavinson. Vol. 159, Translations of mathematical monographs. Providence (RI): American Mathematical Society; 1997. 175 p.
   Google Scholar
• Ismailov VE. Characterization of an extremal sum of ridge functions. J. Comput. Appl. Math. 2007;205:105–115.
   Web of Science ®Google Scholar
• Sternfeld Y. Uniformly separating families of functions. Israel J. Math. 1978;29:61–91.
   Web of Science ®Google Scholar
• Sproston JP, Strauss D. Sums of subalgebras of C(X). J. London Math. Soc. 1992;45:265–278.
   Web of Science ®Google Scholar
• Marshall DE, O’Farrell AG. Uniform approximation by real functions. Fund. Math. 1979;104:203–211.
   Google Scholar
• Rudin W. Functional analysis. McGraw-Hill series in higher mathematics. New York (NY): McGraw-Hill Book Co.; 1973. 397 p.
   Google Scholar
• Maiorov V, Pinkus A. Lower bounds for approximation by MLP neural networks. Neurocomputing. 1999;25:81–91.
   Web of Science ®Google Scholar
• Ismailov VE. On the approximation by neural networks with bounded number of neurons in hidden layers. J. Math. Anal. Appl. 2014;417:963–969.
   Web of Science ®Google Scholar