The network given in the figure is trained by backpropagation algorithm. The sigmoidal activation functions used in the network are parametric $($ai$$s are the parameters and they are updated at each iteration together with the weights$).$ The activation functions are given as $$ a v e v $1111,$ a v e v $2112,$ a v e v $3113,$ a v e v $4114,$ a v e v $5115$ and $$ a v e v $6116$ with a$1=$a$2=$a$3=$a$4=$a$5==1.$ The weights are given as w$1=0\mathrm{.}1,$ w$2=0\mathrm{.}3,$ w$3=0\mathrm{.}4,$ w$4=0\mathrm{.}2,$ w$5=0\mathrm{.}6,$ w$6=0\mathrm{.}5,$ w$7=0\mathrm{.}9,$ w$8=0\mathrm{.}8,$ w$9=0\mathrm{.}1,$ w$10=1\mathrm{.}2,$ w$11=0\mathrm{.}2$ and w$12=1,$ w$13=0\mathrm{.}4,$ w$14=0\mathrm{.}9,$ w$15=0\mathrm{.}5,$ w$16=1\mathrm{.}5.$ Assume: $222121$ E $$ e $$ e $,111$ e $$ d $$ y $,222$ e $$ d $$ y $,1$ d$1$ d$2,0\mathrm{.}2($d$1$ and d$2$ are desired outputs for output neurons and $$ is the learning rate$).($a$)$ For one forward pass, calculate y$1$ and y$2.($b$)$ Write down the update rule for w$9$ and determine the updated value of w$9$ for one iteration. $($c$)$ Write down the update rule for w$1$ and determine the updated value of w$1$ for one iteration. $($d$)$ Write down the update rule for a$1$ and determine the updated value of a$1$ for one iteration.