1 Weight updates Consider a twowlayer feedforward ANN with two inputs (.1 and b one hidden unit 6, and one output unit (1'. This network has ve weights (mm, wig, 1nd}, wdc, wag), where wag represents the threshold weight for unit I. Initialize these weights to the values (.1, .1, .1, .1, .1), then give their values after each of the rst two training iterations of the Backpr'opaga'tion algorithm. Assume learning rate 1"} = 0.3, momentum a = 0.9, incremental weight updates, and the following training examples: a I] d l 0 1 0 l 0 Comments: 0 When the question refers to the "threshold weight", interpret that as in this diagram (where the inputs are at the bottom and the output is at the top): You can treat the nodes in green as units with a xed value of l. Weights 113d} and wan are the threshold weights, AKA biases