论文信息 - Recurrent neural networks as pattern generators

Recurrent neural networks as pattern generators

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.<<ETX>>

V. Petridis | A. Papaikonomou

[1] A. Papaikonomou,et al. A genetic algorithm for training recurrent neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[2] L. B. Lmeida. Backpropagation in perceptrons with feedback , 1988 .

[3] Fernando J. Pineda,et al. GENERALIZATION OF BACKPROPAGATION TO RECURRENT AND HIGH-ORDER NETWORKS. , 1987 .

[4] John H. Holland,et al. Outline for a Logical Theory of Adaptive Systems , 1962, JACM.

[5] Pineda,et al. Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[6] David E. Goldberg,et al. Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[7] Ronald J. Williams,et al. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[8] L. B. Almeida,et al. BACKPROPAGATION IN PERCEPTRONS WITH FEEDBACK , 2022 .

[9] Vassilios Petridis,et al. A hybrid genetic algorithm for training neural networks , 1992 .

[10] Lawrence. Davis,et al. Handbook Of Genetic Algorithms , 1990 .

[11] Barak A. Pearlmutter. Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.