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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics>&l...

Full description

Saved in:
Bibliographic Details
Main Author: Seda Karateke
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/3/453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850200086862102528
author Seda Karateke
author_facet Seda Karateke
author_sort Seda Karateke
collection DOAJ
description 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi mathvariant="double-struck">R</mi><mover><mi>N</mi><mo>¯</mo></mover></msup></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mover><mi>N</mi><mo>¯</mo></mover><mo>∈</mo><mi mathvariant="double-struck">N</mi></mrow></semantics></math></inline-formula>. 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.
format Article
id doaj-art-ad3e9cda16e2459b9ff84bbe4a449394
institution OA Journals
issn 2227-7390
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-ad3e9cda16e2459b9ff84bbe4a4493942025-08-20T02:12:25ZengMDPI AGMathematics2227-73902025-01-0113345310.3390/math13030453Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent FunctionSeda Karateke0Department of Software Engineering, Faculty of Engineering and Natural Sciences, Istanbul Atlas University, 34408 Istanbul, TürkiyeThis 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 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi mathvariant="double-struck">R</mi><mover><mi>N</mi><mo>¯</mo></mover></msup></semantics></math></inline-formula>, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mover><mi>N</mi><mo>¯</mo></mover><mo>∈</mo><mi mathvariant="double-struck">N</mi></mrow></semantics></math></inline-formula>. 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.https://www.mdpi.com/2227-7390/13/3/453multi-layer approximationparameterized half-hyperbolic tangent functionmultivariate trigonometric and hyperbolic neural network approximationmultivariate modulus of continuityiterated approximationmultivariate density function
spellingShingle Seda Karateke
Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent Function
Mathematics
multi-layer approximation
parameterized half-hyperbolic tangent function
multivariate trigonometric and hyperbolic neural network approximation
multivariate modulus of continuity
iterated approximation
multivariate density function
title Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent Function
title_full Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent Function
title_fullStr Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent Function
title_full_unstemmed Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent Function
title_short Complex-Valued Multivariate Neural Network (MNN) Approximation by Parameterized Half-Hyperbolic Tangent Function
title_sort complex valued multivariate neural network mnn approximation by parameterized half hyperbolic tangent function
topic multi-layer approximation
parameterized half-hyperbolic tangent function
multivariate trigonometric and hyperbolic neural network approximation
multivariate modulus of continuity
iterated approximation
multivariate density function
url https://www.mdpi.com/2227-7390/13/3/453
work_keys_str_mv AT sedakarateke complexvaluedmultivariateneuralnetworkmnnapproximationbyparameterizedhalfhyperbolictangentfunction