DocumentCode
3255036
Title
Signal processing with neural networks-I. Signal in noise
Author
Solka, J.L. ; Rogers, George W. ; Harrell
Author_Institution
US Naval Surface Warfare Center, Dahlgren, VA, USA
fYear
1989
fDate
0-0 1989
Abstract
Summary form only given, as follows. Radar signal processing with multilayered perceptrons was investigated. Networks with no hidden layer and a single hidden layer were tested extensively on millimeter wave target returns which had been corrupted with Gaussian noise at a signal to noise level of 3 dB. Performance as a function of network-architecture was characterized.<>
Keywords
computer architecture; computerised signal processing; neural nets; radar theory; 3 dB; SNR; corrupted with Gaussian noise; millimeter wave target returns; multilayered perceptrons; network-architecture; networks with hidden layers; networks without hidden layer; neural networks; radar signal processing; signal in noise; signal to noise level; Computer architecture; Neural networks; Radar theory;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location
Washington, DC, USA
Type
conf
DOI
10.1109/IJCNN.1989.118435
Filename
118435
Link To Document