Title :
Pulse waveform synthesis using recurrent complex-valued neural networks
Author_Institution :
Inst. for Neuroinf., Bonn Univ., Germany
fDate :
27 Jun-2 Jul 1994
Abstract :
An experiment of time-sequential pulse train synthesis using a layered and partially-recurrent complex-valued neural network is reported. A one half of the three-layer complex valued neural network is used to generate sinusoidal oscillation, and the other half is used to synthesize adaptively the intended pulse shapes and sequences. Stable time-sequential pulse signals are obtained after completion of the learning process. This result suggests that the complex-valued neural networks are effectively applicable to pulse-operational neural networks
Keywords :
learning (artificial intelligence); recurrent neural nets; signal processing; waveform analysis; learning process; pulse shapes; pulse waveform synthesis; recurrent complex-valued neural networks; sinusoidal oscillation; three-layer complex valued neural network; time-sequential pulse train synthesis; Electronic mail; Network synthesis; Neural networks; Neurons; Optical pulse shaping; Pulse generation; Pulse shaping methods; Recurrent neural networks; Shape; Signal synthesis;
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
DOI :
10.1109/ICNN.1994.374248