EX$1$: Consider a fully connected neural network in the Figure below:

$x-$longrightarrow$$

a$)$ Assuming the activation function is a Sigmold function, write the analytical expressions for derivatwes with respect to the weights IV $.$ biases b$,$ and input $x.$

b$)$ Assuming the activation fonction is an loencig function, $f(x)=x,$ what would be the derivatives with respect to all the weights $W$ and blases $b?$ Comment on why this activation function is such a bad choice for neural network learning.