Gradient calculations for dynamic recurrent neural networks: a survey
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In this paper, the identification of Duffing's equation by dynamic recurrent neural network (DRNN) is discussed. It is assumed that only states of the Duffing's equation are available and the system is taken as a black box. It is shown that the DRNN can model the dynamics of the Duffing's equation. A numerical example indicates that the forced training method can be used to train the DRNN.