Consider the following equation for gradient descent:

ww$-$nell. D$.$ wl

whereg is the gradient function, I the loss function, and D$,$ the dataset and denotes the learning rate and the corresponding pseudo$-$code for the mini$-$batch variant:

$1.$ for i $=1$ to num$\_$iter $\{$

$2$ shuffle $($data$)$;

$3.$ for batch in get$\_$batches $($data$,$ batch$\_$size$)($

$4.$ gradeval$\_$gradient $($loss$\_$function, batch, w$)$;

ww$-$learning$\_$rate grad:

Identify the line numbers in this code that can be parallelized. Argue how the said lines can be parallelized using a distributed parameter server model. Will there be a difference between shared memory machine model and distributed memory machine model implementation for this. Justify your answer.