Is __call__ in ntm_cell correct?

Hi
I am some kind of confused about the implementation of ntm_cell, especially the __call__() part.
According to the code, it seems that the new_output has nothing to do with the memory part.
Should it be more plausible if the new_output adapts itself with memory part?
`
output_list, hidden_list = self.build_controller(input_, read_list_prev,
output_list_prev,
hidden_list_prev)

# last output layer from LSTM controller
last_output = output_list[-1]

# build a memory
M, read_w_list, write_w_list, read_list = self.build_memory(M_prev,
read_w_list_prev,
write_w_list_prev,
last_output)

# get a new output
new_output, new_output_logit = self.new_output(last_output)
`

Start at ntm_cell.__call__ and trace how build_controller, build_memory, and new_output use their inputs and return values. Determine whether the reported memory/output relationship matches the intended Neural Turing Machine behavior; the issue is done when that behavior is clarified and any required change is covered by a focused check.

Written by the indexing model from the issue text.