Identification of nonlinear systems with a dynamic recurrent neural network
Delgado, A., Kambhampati, C. and Warwick, K. (1995) Identification of nonlinear systems with a dynamic recurrent neural network. In: Fourth International Conference on Artificial Neural Networks, 26-28 June 1995, Cambridge, UK, pp. 318-322.
Full text not archived in this repository.
To link to this article DOI: 10.1049/cp:19950575
Two approaches are presented to calculate the weights for a Dynamic Recurrent Neural Network (DRNN) in order to identify the input-output dynamics of a class of nonlinear systems. The number of states of the identified network is constrained to be the same as the number of states of the plant.
Centaur Editors: Update this record