Q$3)[6$ points$]$ Design a single hidden layer MLP to model the function $f=(-w^{{?}^{?}}z{)}^{{?}^{?}}(xvv-y).$ Assuming simple perceptron: output $=1$ if ${\displaystyle \underset{i}{\overset{?}{}}}{w}_i{x}_i+b_{i}0.$ Clearly show the used weights and biases

Answer:

Q$4)[6$ points$]$ How many neurons needed to design an MLP to detect all points inside the shaded area of the shape given below with $100\%$ accuracy. Justify your answer.

Answer:

Q$5)[6$ points$]$ Given the following MLP$,$ what is the output $y$ for each of the given inputs in the table below? Which boolean function does it represent?

$\backslash$table$[[x1,x2,Y,Y,,],[0,0,,,,],[0,1,,,,],[1,0,,,,],[1,1,,,,]]$