a$)$ How many weights in the convolutional layer do we need to learn?

b$)$ How many ReLu operations are performed on the forward pass? $[2]$

c$)$ How many weights do we need to learn for the entire network? $[2]$

d$)$ Can a fully$-$connected neural network with the same size layers as the above network can

represent any classifier that the above convolutional network can represent?

e$)$ What are the disadvantages of a fully$-$connected neural network compared to a

convolutional neural network with the same size layers?