Fractional approximation by normalized bell and squashing type neural network operators


This article deals with the determination of the fractional rate of convergence to the unit of some neural network operators, namely, the normalized bell and "squashing" type operators. This is given through the moduli of continuity of the involved right and left Caputo fractional derivatives of the approximated function and they appear in the right-hand side of the associated Jackson type inequalities. © 2013 World Scientific Publishing Company.

Publication Title

New Mathematics and Natural Computation