MATLAB: Should I use cross-correlation and auto-correlation to determine the number of delays in a NARX neural network

auto-correlationcross correlationDeep Learning Toolboxfeedback delaysinput delaysnarxneural networks

I'm working with a NARX network to model the response of a dynamic system. I have the data for both the input signal and the system response. In trying to figure out the appropriate number of delays that I need to use (both input and feedback delays), I have come across several references to cross-correlation and auto-correlation. As I understand it, I would pick the delays that correspond to the highest peaks in the auto-correlation and cross-correlation plots, as they are more statistically significant than the others. What I'm not understanding is why is it appropriate to use that in the context of neural networks?

Best Answer

It doesn't matter if it is a neural network or any other nonlinear regression model.
There tends to be a high probability that inputs with significant linear input-output correlations have a significant effect on outputs when a nonlinear regression model is used.
Similarly, there tends to be a high probability that inputs with insignificant linear input-output correlations have an insignificant effect on outputs when a nonlinear regression model is used.
Hope this helps.
Greg
Related Question