Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent Function

This paper deals with a family of normalized multivariate neural network (MNN) operators of complex-valued continuous functions for a multivariate context on a box of RN¯, N¯∈N. Moreover, we consider the case of approximation employing iterated MNN operators. In addition, pointwise and uniform conve...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematics (Basel) Ročník 13; číslo 3; s. 453
Hlavní autor: Karateke, Seda
Médium: Journal Article
Jazyk:angličtina
Vydáno: Basel MDPI AG 01.02.2025
Témata:
Algorithms
Approximation
Artificial intelligence
Banach spaces
Continuity (mathematics)
Datasets
Fuzzy sets
Hyperbolic functions
iterated approximation
multi-layer approximation
Multivariate analysis
multivariate density function
multivariate modulus of continuity
multivariate trigonometric and hyperbolic neural network approximation
Neural networks
Neurons
Operators (mathematics)
parameterized half-hyperbolic tangent function
New York
United States
ISSN:2227-7390, 2227-7390
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper deals with a family of normalized multivariate neural network (MNN) operators of complex-valued continuous functions for a multivariate context on a box of RN¯, N¯∈N. Moreover, we consider the case of approximation employing iterated MNN operators. In addition, pointwise and uniform convergence results are obtained in Banach spaces thanks to the multivariate versions of trigonometric and hyperbolic-type Taylor formulae on the corresponding feed-forward neural networks (FNNs) based on one or more hidden layers.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2227-7390
2227-7390
DOI:10.3390/math13030453