Introduction to Deep Learning / hidden layer

Problem 2 (50pts). The following chart shows a deep neural network with two hidden layers and the loss function is mean squared error (MSE) W(1) W(2) W MSE x Z1 Z2 (W) (n) (d1, ReLu) (dz, tanh) (1) Figure 2: Numbers in the parenthesis indicate the numbers of neurons. [w(1), W12) W]. Note that we always use bias weights at cach layer. Where W = Defining Yrer as a ground truth label, the MSE of the loss function is given by J(W) ( Yrcf) aJ(W) J(W) Compute aw(1) (1) 1