DocumentCode
288826
Title
Noise canceling with autoassociative memory trained by order statistics
Author
Bae, Jinsoo ; Ryu, Young Kwon ; Song, Iickho
Author_Institution
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Daejon, South Korea
Volume
5
fYear
1994
fDate
27 Jun-2 Jul 1994
Firstpage
3431
Abstract
In this paper, noise canceling using an autoassociative memory is considered for possible applications to constant signal detection. The authors use order statistics to help the neural network learn the noise characteristics. In essence, the performance of this neural network is shown to not depend on the distribution of noise, based on simulations for six well known noise probability density functions
Keywords
content-addressable storage; learning (artificial intelligence); neural nets; noise; probability; signal detection; statistics; autoassociative memory; noise canceling; noise characteristics; order statistics; signal detection; Filters; Gaussian noise; Neural networks; Noise cancellation; Noise figure; Noise reduction; Probability density function; Signal detection; Statistical distributions; Statistics;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location
Orlando, FL
Print_ISBN
0-7803-1901-X
Type
conf
DOI
10.1109/ICNN.1994.374788
Filename
374788
Link To Document