Note that x$($i$)$ represents a single input example, and it is a vector of shape Dx $\backslash$times $1($vector of values of the features$).$ Further y$($i$)$ in $\{0,1\}$ is a single output label $($response$)$ and it is a scalar. There are m examples in our dataset. We will use Da$1$ nodes in our first hidden layer and Da$2$ nodes in our second hidden layer.