Consider a neural network with the following structure: Input layer with two neurons $$ and $$ One hidden layer with two neurons $$ and $$ One output layer with one neuron $$ The weights between the input and hidden layer are: $=0\mathrm{.}1=0\mathrm{.}2($weights connecting $$ and $$ to $)=0\mathrm{.}3=0\mathrm{.}4($weights connecting $$ and $$ to $)$ The weights between the hidden layer and output layer are: $=0\mathrm{.}5=0\mathrm{.}6($weights connecting $$ and $$ to $)$ The activation function for both the hidden layer and output layer is the hyperbolic tangent function: $()=$ tanh$()=$The network is trained using binary cross$-$entropy as the loss function: $=1$ where $$ is the target value. $$ log$+1$ log$1$ You are given the following values for the input and target: $=1,=0($target output$)$ Your Task: $$ Draw the computational graph showing all nodes and edges. $$ Perform a forward pass through the network to compute the output $.$ Compute the loss using the given target value. $$ Perform backpropagation to compute the gradients of the loss with respect to weight $.$ Update the weight using gradient descent with a learning rate $=0\mathrm{.}1$