Complex-Valued Neural Networks: A Comprehensive Survey

Complex-valued neural networks (CVNNs) have shown their excellent efficiency compared to their real counter-parts in speech enhancement, image and signal processing. Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs. Since CV...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/CAA journal of automatica sinica Vol. 9; no. 8; pp. 1406 - 1426
Main Authors: Lee, ChiYan, Hasegawa, Hideyuki, Gao, Shangce
Format: Journal Article
Language:English
Published: Piscataway Chinese Association of Automation (CAA) 01.08.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Faculty of Engineering,University of Toyama,Toyama 930-8555,Japan
Subjects:
Algorithms
Complex activation function
complex backpropagation algorithm
complex-valued learning algorithm
complex-valued neural network
deep learning
Image enhancement
Image segmentation
Machine learning
Magnetic resonance imaging
Neural networks
Pattern classification
Recurrent neural networks
Signal processing
Signal processing algorithms
Speech enhancement
Speech processing
Wind forecasting
Complex activation function
complex-valued neural network
deep learning
complex backpro-pagation algorithm
complex-valued learning algorithm
ISSN:2329-9266, 2329-9274
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Complex-valued neural networks (CVNNs) have shown their excellent efficiency compared to their real counter-parts in speech enhancement, image and signal processing. Researchers throughout the years have made many efforts to improve the learning algorithms and activation functions of CVNNs. Since CVNNs have proven to have better performance in handling the naturally complex-valued data and signals, this area of study will grow and expect the arrival of some effective improvements in the future. Therefore, there exists an obvious reason to provide a comprehensive survey paper that systematically collects and categorizes the advancement of CVNNs. In this paper, we discuss and summarize the recent advances based on their learning algorithms, activation functions, which is the most challenging part of building a CVNN, and applications. Besides, we outline the structure and applications of complex-valued convolutional, residual and recurrent neural networks. Finally, we also present some challenges and future research directions to facilitate the exploration of the ability of CVNNs.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2329-9266
2329-9274
DOI:10.1109/JAS.2022.105743