4. A. The neural network shown in the following figure is presented with the input pattern [0, 1] and target output 1. 0.3 0.6 0.4 -0.2 -0.1 Output -0.3 X2 0.1 0.4 0.5 Figure 4. Neural network diagram I. Derive the expression to Z, Z, and Y. Calculate the values of Z, Z, and Y. [05 Marks) II. Find the new weights for the network given using back-propagation algorithm. Use learning rate of o =0.3 and sigmoid activation function. [07 Marks) B. The neural network with linear active units is shown in the figure below. The output of each unit (sum of the weighted inputs) is multiplied by a constant K value. W: W9 wz W13 W3 24 W10 w Output WS 2: WIL WE W14 W7 W12 Figure S. Neural network diagram 6 X/02 X/ REV.00/00.00.0000 I. Is it possible for any function that can be represented by the above network to also be represented using a single unit network? If so, draw such a network, including the weights and activation function. If not, explain why not. [08 Marks] II. Is it possible for any function that can be represented by the above network to also be represented by linear regression? If so, provide an equation for Y. If not, explain why not. [05 Marks)