Please explain as best you can how to get the answer(with theory) and I will give you a thumbs up. Don't simply use chat GPT.

(c) Fig. Q2 shows the process of statistics pooling in feature representation learning. Fig. Q2 (i) Express the vector u in terms of ht, for all t=1,,T. (6 marks) (ii) Explain why statistics pooling enables the network to receive vector sequences of arbitrary length, i.e., the value of T can be different for training and test samples. (4 marks)