四元数神经网络的通用近似与逼近优势.pdfVIP

计算机研究与发展

Journal

of

Computer

Research

and

Development62（5）：1205−1215，2025

四元数神经网络的通用近似与逼近优势

吴锦辉姜远

（计算机软件新技术全国重点实验室

（南京大学）南京210023）

（南京大学人工智能学院南京210023）

（wujh@）

UniversalApproximationandApproximationAdvantagesofQuaternion-Valued

NeuralNetworks

Wu

Jinhui

and

Jiang

Yuan

（NationalKeyLaboratoryforNovelSoftwareTechnology(NanjingUniversity),Nanjing210023）

（SchoolofArtificialIntelligence,NanjingUniversity,Nanjing210023）

AbstractQuaternion-valued

neural

networks

extend

real-valued

neural

networks

to

the

algebra

of

quaternions.

Quaternion-valued

neural

networks

achieve

higher

accuracy

or

faster

convergence

than

real-valued

neural

networks

in

some

tasks,

such

as

singular

point

compensation

in

polarimetric

synthetic

aperture,

spoken

language

understanding,

and

radar

robot

control.

The

performance

of

quaternion-valued

neural

networks

is

widely

supported

by

empirical

studies,

but

there

are

few

studies

about

theoretical

properties

of

quaternion-valued

neural

networks,

especially

why

quaternion-valued

neural

networks

can

be

more

efficient

than

real-valued

neural

networks.

In

this

paper,

we

investigate

theoretical

properties

of

quaternion-valued

neural

networks

and

the

advantages

of

quaternion-valued

neural

networks

compared

with

real-valued

neural

networks

from

the

perspective

of

approximation.

Firstly,

we

prove

the

universal

approximation

of

quaternion-valued

neural

networks

with

a

non-split

ReLU

(rectified

linear

unit)-type

activation

function.

Secondly,

we

demonstrate

the

approximation

advantages

of

quaternion-valued

neural

networks

compared

with

real-valued

neural

networks.

For

split

ReLU-type

activation

functions,

we

show

that

one-hidden-layer

r