Given the data consisting of two classes

Blue $\{[-1-1],[11],[22]\}$

Red $\{[0-1],[-10],[21],[12]\}$

a$)$ Construct a network consisting of two perceptrons to classify the above data. Determine the solution by hand and with Python.

b$)$ Classify the above data in Question $2$ with $($i$)$ using the sigmoid and $($ii$)$ the sign$(.)$function$.$ Do you see any difference in the two solutions?

c$)$ Given the vector $[$x$1$ x$2]=[21\mathrm{.}75]$T determine its class using the ReLU as the activation function. Determine its class using the weights obtained in Question $5$ and the sigmoid function. What is the estimated probability value? What can be the advantage of using a probability value?