Complex-valued neural networks: the merits and their origins

Authors:
Akira Hirose
Affiliations:
Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo, Japan
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 14
Cited 6

Applications of complex-valued neural networks to coherent optical computing using phase-sensitive detection scheme

Information Sciences—Applications: An International Journal
Plastic mine detecting radar system using complex-valued self-organizing map that deals with multiple-frequency interferometric images

Neural Networks - 2004 Special issue: New developments in self-organizing systems
Complex-Valued Neural Networks (Studies in Computational Intelligence)

Complex-Valued Neural Networks (Studies in Computational Intelligence)
An Augmented Extended Kalman Filter Algorithm for Complex-Valued Recurrent Neural Networks

Neural Computation
Models of orthogonal type complex-valued dynamic associative memories and their performance comparison

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Nonlinear adaptive prediction of complex-valued signals by complex-valued PRNN

IEEE Transactions on Signal Processing
Behavior control of coherent-type neural networks by carrier-frequency modulation

IEEE Transactions on Neural Networks
CGHA for principal component extraction in the complex domain

IEEE Transactions on Neural Networks
Landmine detection and classification with complex-valued hybrid neural network using scattering parameters dataset

IEEE Transactions on Neural Networks
Improvements of Complex-Valued Hopfield Associative Memory by Using Generalized Projection Rules

IEEE Transactions on Neural Networks
Developmental Learning With Behavioral Mode Tuning by Carrier-Frequency Modulation in Coherent Neural Networks

IEEE Transactions on Neural Networks
A Class of Complex ICA Algorithms Based on the Kurtosis Cost Function

IEEE Transactions on Neural Networks
Complex ICA by Negentropy Maximization

IEEE Transactions on Neural Networks
Blur Identification by Multilayer Neural Network Based on Multivalued Neurons

IEEE Transactions on Neural Networks

Recent progress in applications of complex-valued neural networks

ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
Determination of complex-valued parametric model coefficients using artificial neural network technique

Advances in Artificial Neural Systems
A novel signal diagnosis technique using pseudo complex-valued autoregressive technique

Expert Systems with Applications: An International Journal
Single layer complex valued neural network with entropic cost function

ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Fixed points of complex-valued bidirectional associative memory

Journal of Computational and Applied Mathematics
Artificial neural network based autoregressive modeling technique with application in voice activity detection

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses what the merits of complex-valued neural networks (CVNNs) arise from. First we look back the mathematical history to elucidate the features of complex numbers, in particular to confirm the importance of the phase-and-amplitude viewpoint for designing and constructing CVNNs to enhance the features. The viewpoint is essential in general to deal with waves such as electromagnetic-wave and lightwave. Then we point out that, although we represent a complex number as an ordered pair of real numbers for example, we can reduce ineffective degree of freedom in learning or self-organization in CVNNs to achieve better generalization characteristics. This wave-oriented merit is useful widely for general signal processing with Fourier synthesis or in frequency-domain treatment through Fourier transform.