3. Neural Networks. (20 points) Consider a neural network, with Ni=2 input units, x= (x1,x2),Nh=3 hidden units with ReLU activations and one output unit for regression, zjHy=k=1NiWjkHxk+bjH,ujH=max{0,zjH},j=1,,Nh=k=1NhWkOukH+bO, (a) (5 points) Suppose that WH=101011,bH=0.513 Write equations for zjH in terms of x for j=1,2,3. (b) (5 points) Draw the region of inputs (x1,x2) where ujH>0 for all j. (c) (5 points) Assuming you were given the following training data set, and the parameters of the hidden layer are as above. What parameter WO and bO, the weight and bias for the output layer that minimizes the MSE? What is the MSE of the training set with those parameters? (d) (5 points) You are given data x, y as well as weights and biases Wh, bh for the hidden layer. Write a few lines of python code to fit wo, bo for the output layer by minimizing the MSE. You may assume you have a function