The graph represents gradient flow of a four$-$hidden layer neural network which is trained using sigmoid

activation function per epoch of training. The neural network suffers with the vanishing gradient problem.

$10$ Speedofleaming:$4$hiddenIayers

$0$

$10$

B

$10$

$10$ D

$10$

$200400$

Number of epochs of training

$100300$

Which of the following statements is true?

$(4$ Hidden layer $1$ corresponds to A$,$ Hidden layer $2$ corresponds to B$,$ Hidden layer $3$ corresponds to C and Hidden

layer $4$ corresponds to D$.$

Hidden layer $1$ corresponds to D$,$ Hidden layer $2$ corresponds to C$,$ Hidden layer $3$ corresponds to Band Hidden

layer $4$ corresponds to A$.$