Abstract
Multi-Layer Perceptron network modeling for nonlinear dynamic systems is studied. The situations that only a relatively small number of training data is available and that the training data does not cover all system dynamics are mainly concerned. An improved method is proposed by training with two sets of data, which is shown to give better generalization performance in the above-mentioned circumstances.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
