Title :
Recurrent neural networks as pattern generators
Author :
Petridis, V. ; Papaikonomou, A.
Author_Institution :
Dept. of Electr. Eng., Thessaloniki Univ., Greece
fDate :
27 Jun-2 Jul 1994
Abstract :
A fully connected recurrent ANN model is proposed as a generator of stable limit cycles. A hybrid genetic algorithm is used for training the network model. The behaviour of the model is presented through a number of simulation experiments and the stability of the generated limit cycles is tested under several conditions
Keywords :
learning (artificial intelligence); limit cycles; recurrent neural nets; stability; fully connected recurrent ANN model; hybrid genetic algorithm; limit cycles; pattern generators; recurrent neural networks; simulation experiments; stability; Artificial neural networks; Genetic algorithms; Genetic mutations; Limit-cycles; Performance analysis; Recurrent neural networks; Signal analysis; Signal generators; Stability; Testing;
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.1994.374295
