Consider the following network structure. You can assume the initial weights. Assume bias

to be zero for easier computations. Given that $\{$:$($:$x_1,x_2,$hat$(y{)}_1,$hat$(y{)}_2$::$)$ where hat$(y)$ is

the target. Assume $=0\mathrm{.}9$ and $=0\mathrm{.}01.$

$($a$)$ Compute the forward propagation and generate the output. Use Relu for hidden layers

and Sigmoid activation function for output layer.

$($b$)$ Compute the Softmax loss function for both outputs.

$($c$)$ Let the initial weights that assumed be the weights $[$at time $($t$-1).$ Compute the weights

$v_{21},w_{12}$ and $w_{22}$ at time $t$ using SGD$.$

$($d$)$ Let the weight at time $t$ be the ones computed in part $($c$).$ Compute the weights $v_{21},$

$w_{12}$ and $w_{22}$ at $(t+1)$ when momentum is used.