12:55 8 6 9 46 .1 37% 8 Question 5 (8 marks, 4 each) (a) What are the main differences between a feedforward neural network and a recurrent neural network? (b) Let y1, y2, ..., y100 be a time series. The last three observations are yos = 2, ygg = 1 and y100 = 2. You use a simple recurrent neural network for forecasting ht = o(0.lyt + 0.1ht-1 - 0.5), 1 = 1+2h+ + et+1. where the e are random error with mean 0, and o(x) =1/(1+e-) is the sigmoid function. The forecast for the last time period is 3100 = 1.5. Compute the point forecast for y101. A O