Max-product neural network and quasi-interpolation operators activated by sigmoidal functions (Q2630379): Difference between revisions
From MaRDI portal
Set profile property. |
Set OpenAlex properties. |
||
Property / full work available at URL | |||
Property / full work available at URL: https://doi.org/10.1016/j.jat.2016.05.001 / rank | |||
Normal rank | |||
Property / OpenAlex ID | |||
Property / OpenAlex ID: W2406122930 / rank | |||
Normal rank |
Revision as of 21:20, 19 March 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Max-product neural network and quasi-interpolation operators activated by sigmoidal functions |
scientific article |
Statements
Max-product neural network and quasi-interpolation operators activated by sigmoidal functions (English)
0 references
27 July 2016
0 references
The max-product neural network (NN) and quasi-interpolation (QI) operators are introduced and studied in the present article. The density functions considered as kernels for such operators are generated by certain finite linear combination of sigmoidal functions, and from them inherit very useful approximation properties. The convergence and the rate of approximation for the max-product NN and QI operators are studied. Estimates involving the modulus of continuity of the functions being approximated have been derived. Several examples are provided together with some applications and graphical representations.
0 references
sigmoidal functions
0 references
neural networks operators
0 references
uniform approximation
0 references
order of approximation
0 references
max-product operators
0 references