Multivariate Fuzzy Perturbed Neural Network Operators Approximation


Authors

George A. Anastassiou - Department of Mathematical Sciences, University of Memphis, Memphis, TN 38152, U.S.A.


Abstract

This article studies the determination of the rate of convergence to the unit of each of three newly introduced here multivariate fuzzy perturbed normalized neural network operators of one hidden layer. These are given through the multivariate fuzzy modulus of continuity of the involved multivariate fuzzy number valued function or its high order fuzzy partial derivatives and that appears in the right-hand side of the associated fuzzy multivariate Jackson type inequalities. The multivariate activation function is very general, especially it can derive from any sigmoid or bell-shaped function. The right hand sides of our multivariate fuzzy convergence inequalities do not depend on the activation function. The sample multivariate fuzzy functionals are of Stancu, Kantorovich and Quadrature types. We give applications for the first fuzzy partial derivatives of the involved function.


Share and Cite

  • Share on Facebook
  • Share on Twitter
  • Share on LinkedIn
ISRP Style

George A. Anastassiou, Multivariate Fuzzy Perturbed Neural Network Operators Approximation, Journal of Nonlinear Sciences and Applications, 7 (2014), no. 6, 383--406

AMA Style

Anastassiou George A., Multivariate Fuzzy Perturbed Neural Network Operators Approximation. J. Nonlinear Sci. Appl. (2014); 7(6):383--406

Chicago/Turabian Style

Anastassiou, George A.. "Multivariate Fuzzy Perturbed Neural Network Operators Approximation." Journal of Nonlinear Sciences and Applications, 7, no. 6 (2014): 383--406


Keywords


MSC


References