A practical approach for training dynamic recurrent neural networks: use of Apriori information
R. Craddock · 1998
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 is it modelling.