How can I use an algorithm for traning a NARX network and optimize another model in the same time ?

Knowing that the training algorithm is an optimisation method, I want to optimize the parameters of NARX network and another model (hybridization), with one algorithm in the same time. is that possible ? if yes, can I use the algorithm generated with "neural network time series tool" ?

Answer 1

[Greg Heath]

Just because I've never heard of it in my 3-decade experience with NNs doesn't mean it can't be done.

For regression and classification the easiest case would be if there were the same number of examples. Then inputs and targets could be vertically concatenated ( e.g., [input1 ; input2 ].

However in most cases, separate training would be faster if not more accurate.

It can also be done for timeseries. However, the delays have to be the same.

I see no advantage and do not recommend it.

Hope this helps.

Greg

[taytob]

Thank you for your answer and recommendation, I think that it will be complicate and will take a long time to do it.