Title :
Parallel bit-stream neurohardware for blind separation of sources
Author :
Fanghänel, Karsten ; Köllmann, Kuno ; Zeidler, H.C. ; Plessmann, Ralf ; Riemschneider, Karl-Ragmar
Author_Institution :
Univ. der Bundeswehr Hamburg, Germany
Abstract :
The use of digital stochastic computing is proposed to realize a recurrent network for blind separation of undelayed linearly superposed signals into their original components. The stochastic representation of signals allows one to design very simple digital processing elements to implement all the operations necessary for the algorithm of Herault and Jutten (1986). A first hardware implementation has been designed and the experimental results are presented
Keywords :
CMOS digital integrated circuits; VLSI; digital signal processing chips; learning (artificial intelligence); neural chips; neural net architecture; parallel architectures; recurrent neural nets; signal representation; stochastic processes; VLSI; blind source separation; digital CMOS; digital processing elements; digital stochastic computing; experimental results; hardware implementation; learning algorithm; parallel bit-stream neurohardware; recurrent network; stochastic signal representation; undelayed linearly superposed signals; Algorithm design and analysis; Clocks; Computer networks; Hardware; Nonlinear distortion; Sensor arrays; Signal design; Signal processing; Signal processing algorithms; Stochastic processes;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on
Conference_Location :
Munich
Print_ISBN :
0-8186-7919-0
DOI :
10.1109/ICASSP.1997.604860
