Title :
A novel recurrent network for signal processing
Author :
Rao, Bhaskar D. ; Gorodnitsky, Irina F.
Author_Institution :
Dept. of Electr. & Comput. Eng., California Univ., San Diego, La Jolla, CA, USA
Abstract :
A new recurrent network is developed for the signal processing applications of spectral estimation, direction of arrival estimation, and pattern classification. For the development of the network, the above problems are posed as linear inverse problems with sparseness constraints. The results are provided to support the usefulness of the network
Keywords :
direction-of-arrival estimation; inverse problems; pattern classification; recurrent neural nets; signal processing; spectral analysis; direction of arrival estimation; linear inverse problems; pattern classification; recurrent neural net; signal processing; sparseness constraints; spectral estimation; Application software; Associative memory; Convergence; Direction of arrival estimation; Inverse problems; Pattern recognition; Prototypes; Signal processing; Signal processing algorithms; Vectors;
Conference_Titel :
Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop
Conference_Location :
Linthicum Heights, MD
Print_ISBN :
0-7803-0928-6
DOI :
10.1109/NNSP.1993.471878
