Presentation 2009-05-25
Advantages and their origins of complex-valued neural networks
Akira HIROSE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We discuss the merits of complex-valued neural networks (CVNNs) and their origin. 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.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Complex number / ordered pair of real numbers / real 2×2 matrix representation / generalization
Paper # NC2009-2
Date of Issue

Conference Information
Committee NC
Conference Date 2009/5/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Advantages and their origins of complex-valued neural networks
Sub Title (in English)
Keyword(1) Complex number
Keyword(2) ordered pair of real numbers
Keyword(3) real 2×2 matrix representation
Keyword(4) generalization
1st Author's Name Akira HIROSE
1st Author's Affiliation Department of Electric Engineering and Information Systems, The University of Tokyo()
Date 2009-05-25
Paper # NC2009-2
Volume (vol) vol.109
Number (no) 53
Page pp.pp.-
#Pages 6
Date of Issue