Reconstruct shifted values after training a dynamic neural network ?

I'm implementing a dynmaic neural network that has an input delay and also a feedback delay. After training and simulating my neural net I observed that the output has been shifted respectively with the number of steps of the my time delay. Is there a way to reconstruct the lost values?

Answer 1

[Greg Heath]

They are not lost.

It takes multiple input values to yield 1 output value.

Therefore you cannot have as many output time values as input time values.

Hope this helps.

Thank you for fomally accepting my answer

Greg