DocumentCode
453138
Title
Investigation on generalization when NN used as predistorter of PA with memory
Author
Chen, Kaiya ; Wang, Minxi ; Niu, Wei
Author_Institution
Electromagn. Inst., Southwest Jiaotong Univ., Chengdu, China
Volume
2
fYear
2005
fDate
4-7 Dec. 2005
Abstract
Neural network (NN) can be trained as a predistorter which linearlizes nonlinear power amplifier with memory (NLPAWM). Direct learning architecture is proposed to make NN generalize well, for the train inputs sampled from square root raised cosine filter (SRRCF) can represent the actual inputs more accurately. Simulation and analyses confirm that this architecture is effective.
Keywords
linearisation techniques; neural nets; power amplifiers; wideband amplifiers; direct learning architecture; linearization; neural network; nonlinear power amplifier; square root raised cosine filter; Analytical models; Broadband amplifiers; Demodulation; Interchannel interference; Mathematical model; Memory architecture; Neural networks; Nonlinear distortion; Power amplifiers; Transmitters;
fLanguage
English
Publisher
ieee
Conference_Titel
Microwave Conference Proceedings, 2005. APMC 2005. Asia-Pacific Conference Proceedings
Print_ISBN
0-7803-9433-X
Type
conf
DOI
10.1109/APMC.2005.1606479
Filename
1606479
Link To Document