Given H $=$

$123$

$456$

as an input, compute the gradients of the output with respect

to this input for the following activation layers. Show your answer in tensor form by having

a Jacobian matrix for each observation.

$($a$)$ A ReLU layer

$($b$)$ A Softmax layer

$($c$)$ A Logistic Sigmoid Layer

$($d$)$ A Tanh Layer

$($e$)$ A Linear Layer