What is the difference between tapped delay line and sliding window in a neural network?

Question

I'm trying to model some time series data, and I've been reading about tapped delay line and sliding window to transform the input data.

In my understanding a sliding window with windows size 1 shifts the inputs by one at each time step and feeds them back to a feed forward neural network.

target| input
     2| 1 0
     3| 2 1
     4| 3 2
     5| 4 3
     6| 5 4
     7| 6 5

In my understanding, a tapped delay line with delay 2 takes the two most recent inputs and outputs and feeds them back to a recurrent neural network

y(t) = f(x(t-1),y(t-1))

Is there a difference? Why are there different names? Please correct me if I'm wrong.

Answer 1

I thought the sliding window algorithm differs from the tapped delay line. For the former, the whole data structure that is ordered and iterable like an array or a string is given and the result would just be to find the maximum or minimum element from every n element in that given array; but when we apply “delay taps” the ensuing target at each step is not given and should be generated and hence that whole data structure is generated and the result of the algorithm.