|
|
 |
| |
|
|
|
Composition of Activation Functions and the Reduction to Finite Domain at Fractional and Fuzzy Framework |
|
|
|
PP: 69-86 |
|
|
doi:10.18576/pfda/120105
|
|
|
|
Author(s) |
|
|
|
George A. Anastassiou,
|
|
|
|
Abstract |
|
|
| This work takes up the aim of the determination of the rate of fractional and fuzzy pointwise and uniform convergences to the unit operator of the ”normalized cusp fuzzy neural network operators”. The cusp is a compact support activation function, which derives by the composition of two general activation functions having as domain the whole real line. These convergences are given via the moduli of continuity of the engaged fuzzy right and left fractional derivatives or just the modulus of continuity of the function under approximation, in the form of Jackson type inequalities. The composition of activation functions aims to more flexible and powerful neural networks, introducing for the first time the reduction of infinite domains to the one domain of compact support. |
|
|
|
|
|
|
|
