Abstract
In this chapter, the complex Backpropagation (BP) algorithm for the complex backpropagation neural networks (BPN) consisting of the suitable node activation functions having multi-saturated output regions is presented and analyzed by the benchmark testing. And then the complex BPN is utilized as nonlinear adaptive equalizers that can deal with both quadrature amplitude modulation (QAM) and phase shift key (PSK) signals of any constellation sizes. In addition, four nonlinear blind equalization schemes using complex BPN for M-ary QAM signals are described and their learning algorithms are presented. The presented complex BP equalizer (CBPE) gives, compared with conventional linear complex equalizers, an outstanding improvement with respect to bit error rate (BER) when channel distortions are nonlinear.
| Original language | English |
|---|---|
| Title of host publication | Complex-Valued Neural Networks |
| Subtitle of host publication | Utilizing High-Dimensional Parameters |
| Publisher | IGI Global |
| Pages | 194-235 |
| Number of pages | 42 |
| ISBN (Print) | 9781605662145 |
| DOIs | |
| Publication status | Published - 2009 Dec 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Science(all)
Cite this
}
Learning algorithms for complex-valued neural networks in communication signal processing and adaptive equalization as its application. / You, Cheolwoo; Hong, Daesik.
Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters. IGI Global, 2009. p. 194-235.Research output: Chapter in Book/Report/Conference proceeding › Chapter
TY - CHAP
T1 - Learning algorithms for complex-valued neural networks in communication signal processing and adaptive equalization as its application
AU - You, Cheolwoo
AU - Hong, Daesik
PY - 2009/12/1
Y1 - 2009/12/1
N2 - In this chapter, the complex Backpropagation (BP) algorithm for the complex backpropagation neural networks (BPN) consisting of the suitable node activation functions having multi-saturated output regions is presented and analyzed by the benchmark testing. And then the complex BPN is utilized as nonlinear adaptive equalizers that can deal with both quadrature amplitude modulation (QAM) and phase shift key (PSK) signals of any constellation sizes. In addition, four nonlinear blind equalization schemes using complex BPN for M-ary QAM signals are described and their learning algorithms are presented. The presented complex BP equalizer (CBPE) gives, compared with conventional linear complex equalizers, an outstanding improvement with respect to bit error rate (BER) when channel distortions are nonlinear.
AB - In this chapter, the complex Backpropagation (BP) algorithm for the complex backpropagation neural networks (BPN) consisting of the suitable node activation functions having multi-saturated output regions is presented and analyzed by the benchmark testing. And then the complex BPN is utilized as nonlinear adaptive equalizers that can deal with both quadrature amplitude modulation (QAM) and phase shift key (PSK) signals of any constellation sizes. In addition, four nonlinear blind equalization schemes using complex BPN for M-ary QAM signals are described and their learning algorithms are presented. The presented complex BP equalizer (CBPE) gives, compared with conventional linear complex equalizers, an outstanding improvement with respect to bit error rate (BER) when channel distortions are nonlinear.
UR - http://www.scopus.com/inward/record.url?scp=84900239955&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84900239955&partnerID=8YFLogxK
U2 - 10.4018/978-1-60566-214-5.ch009
DO - 10.4018/978-1-60566-214-5.ch009
M3 - Chapter
SN - 9781605662145
SP - 194
EP - 235
BT - Complex-Valued Neural Networks
PB - IGI Global
ER -