Consider a neural net with one hidden layer, two inputs 'a' and 'b', one hidden unit 'c', and one output unit (node) 'd'. The activation function is the sigmoid for each node. This network has five weights (w_ac, w_bc, w_0c, w_cd, w_0d), where w_0i represents the bias or threshold weight for unit i. Initialize these weights to the values (0.3,0.3,0.3,0.3,0.3), then give their values after each of the first two training iterations of Backpropagation algorithm. Assume learning rate (step size) of 0.2, stochastic (incremental) gradient descent (without momentum), and the following training examples:

	a	b	d
x_1	1	0	1
x_2	0	1	0