Nature of complex number and complex-valued neural networks

We discuss the nature of complex number and its effect on complex-valued neural networks (CVNNs). After we review some examples of CVNN applications, we look back at the mathematical history to elucidate the features of complex number, in particular to confirm the importance of the phase-and-amplitude viewpoint for designing and constructing CVNNs to enhance the features. This 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 merit is significantly useful not only for waverelated signal processing but also for general processing with frequency-domain treatment through Fourier transform.

[1]  E. T. Copson,et al.  An introduction to the theory of functions of a complex variable , 1950 .

[2]  B. Widrow,et al.  The complex LMS algorithm , 1975, Proceedings of the IEEE.

[3]  Henry Leung,et al.  The complex backpropagation algorithm , 1991, IEEE Trans. Signal Process..

[4]  Akira Hirose,et al.  Dynamics of fully complex-valued neural networks , 1992 .

[5]  Cris Koutsougeras,et al.  Complex domain backpropagation , 1992 .

[6]  Francesco Piazza,et al.  On the complex backpropagation algorithm , 1992, IEEE Trans. Signal Process..

[7]  Mitsuo Takeda,et al.  Complex neural fields with a Hopfield-like energy function and an analogy to optical fields generated in phase-conjugate resonators , 1992 .

[8]  Akira Hirose,et al.  Continuous complex-valued back-propagation learning , 1992 .

[9]  Donald L. Birx,et al.  A complex mapping network for phase sensitive classification , 1993, IEEE Trans. Neural Networks.

[10]  Akira Hirose,et al.  Applications of complex-valued neural networks to coherent optical computing using phase-sensitive detection scheme , 1994 .

[11]  A Hirose,et al.  Coherent optical neural networks that have optical-frequency-controlled behavior and generalization ability in the frequency domain. , 1996, Applied optics.

[12]  Akira Hirose,et al.  Behavior control of coherent-type neural networks by carrier-frequency modulation , 1996, IEEE Trans. Neural Networks.

[13]  Yuanliang Ma,et al.  CGHA for principal component extraction in the complex domain , 1997, IEEE Trans. Neural Networks.

[14]  Akira Hirose,et al.  Adaptive Complex-Amplitude Texture Classifier that Deals with Both Height and Reflectance for Interferometric SAR Images , 2000 .

[15]  Hiroshi Sawada,et al.  Polar coordinate based nonlinear function for frequency-domain blind source separation , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  Akira Hirose,et al.  Complex-Valued Neural Networks: Theories and Applications , 2003 .

[17]  Akira Hirose,et al.  Plastic mine detecting radar system using complex-valued self-organizing map that deals with multiple-frequency interferometric images , 2004, Neural Networks.

[18]  Danilo P. Mandic,et al.  Nonlinear adaptive prediction of complex-valued signals by complex-valued PRNN , 2005, IEEE Transactions on Signal Processing.

[19]  Akira Hirose,et al.  Beamforming of ultra-wideband pulses by a complex-valued spatio-temporal multilayer neural network , 2005, Int. J. Neural Syst..

[20]  Akira Hirose,et al.  Frequency-multiplexed logic circuit based on a coherent optical neural network. , 2005, Applied optics.

[21]  Jussi Tohka,et al.  Automated diagnosis of brain tumours astrocytomas using probabilistic neural network clustering and support vector machines , 2005, Int. J. Neural Syst..

[22]  Nirmal K. Bose,et al.  Landmine detection and classification with complex-valued hybrid neural network using scattering parameters dataset , 2005, IEEE Transactions on Neural Networks.

[23]  Akira Hirose,et al.  Adaptive Plastic-Landmine Visualizing Radar System: Effects of Aperture Synthesis and Feature-Vector Dimension Reduction , 2005, IEICE Trans. Electron..

[24]  Akira Hirose,et al.  Efficient generation of holographic movies with frame interpolation using a coherent neural network , 2006, IEICE Electron. Express.

[25]  Akira Hirose,et al.  Developmental Learning With Behavioral Mode Tuning by Carrier-Frequency Modulation in Coherent Neural Networks , 2006, IEEE Transactions on Neural Networks.

[26]  D.-L. Lee,et al.  Improvements of Complex-Valued Hopfield Associative Memory by Using Generalized Projection Rules , 2006, IEEE Transactions on Neural Networks.

[27]  Xiao-Jing Wang,et al.  Mean-Driven and Fluctuation-Driven Persistent Activity in Recurrent Networks , 2007, Neural Computation.

[28]  Yasuaki Kuroe,et al.  Models of Orthogonal Type Complex-Valued Dynamic Associative Memories and Their Performance Comparison , 2007, ICANN.

[29]  Akira Hirose,et al.  Walled LTSA Array for Rapid, High Spatial Resolution, and Phase-Sensitive Imaging to Visualize Plastic Landmines , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[30]  S. L. Goh,et al.  An Augmented Extended Kalman Filter Algorithm for Complex-Valued Recurrent Neural Networks , 2007, Neural Computation.

[31]  Tülay Adali,et al.  Complex ICA by Negentropy Maximization , 2008, IEEE Transactions on Neural Networks.

[32]  Akira Hirose,et al.  Multiple-Mode Selection of Walled-LTSA Array Elements for High-Resolution Imaging to Visualize Antipersonnel Plastic Landmines , 2008, IEEE Geoscience and Remote Sensing Letters.

[33]  Jacek M. Zurada,et al.  Blur Identification by Multilayer Neural Network Based on Multivalued Neurons , 2008, IEEE Transactions on Neural Networks.

[34]  Akira Hirose,et al.  High-quality frame interpolation in computer generated holographic movies using coherent neural networks with a hybrid learning method. , 2008, Applied optics.

[35]  Hualiang Li,et al.  A Class of Complex ICA Algorithms Based on the Kurtosis Cost Function , 2008, IEEE Transactions on Neural Networks.

[36]  Akira Hirose,et al.  Frequency-Multiplexing Ability of Complex-Valued Hebbian Learning in Logic Gates , 2008, Int. J. Neural Syst..

[37]  Akira Hirose,et al.  Improvement of Plastic Landmine Visualization Performance by Use of Ring-CSOM and Frequency-Domain Local Correlation , 2009, IEICE Trans. Electron..

[38]  Akira Hirose,et al.  Singular Unit Restoration in Interferograms Based on Complex-Valued Markov Random Field Model for Phase Unwrapping , 2009, IEEE Geoscience and Remote Sensing Letters.

[39]  Akira Hirose,et al.  Complex-Valued Neural Networks , 2006, Studies in Computational Intelligence.