A practical approach for training dynamic recurrent neural networks: use of Apriori information
Craddock, R. J., Kambhampati, C., Tham, M. and Warwick, K. (1998) A practical approach for training dynamic recurrent neural networks: use of Apriori information. In: The UKACC '98 Conference on Control, 1-4 September 1998, Swansea, UK, pp. 324-329.
Full text not archived in this repository.
To link to this article DOI: 10.1049/cp:19980249
Presents a technique for incorporating a priori knowledge from a state space system into a neural network training algorithm. The training algorithm considered is that of chemotaxis and the networks being trained are recurrent neural networks. Incorporation of the a priori knowledge ensures that the resultant network has behaviour similar to the system which it is modelling.