II: Consider the following code.

a). Fill in the blanks and test the code.

b). What is the output of the code.

(1) Import numpy using alias "p" below: def nonline, der i False): IF(deriv=True): return x*(1-x) return 1/(1+np.exp(-x)) X = np.array([[0,0,1). [0,1,1). (1,0,1). [1,1,1]]) y = np.array([], [0]) np.randos. seed (1) randomly initialize our weights with mean syne = 2 p.random.random((2,4)) - 1 syni - 2nprandon.random((4,1)) - 1 For ) in range(69000): Feed forward through Layers O, 1. and 2 10 x 11 - nonlin(np. dot (10, syne) 12 - nonlin(np.dot(11, syni)) (2) what is the difference between y and y-hat? 12 error = (a) print 12 error in every 10000 iterations print("Error: + strinpeas (np.abs(12 errors) In What direction is the target value were we really sure? If so, don't change too much 12_delta 12 error onlin(12, deriveTrue how much did each 11 value contribute to the 12 cror(according to the we 11 error - 12 delta.dat (sy2.1) in what direction is the target 117 were we really sure if 19, don't change too much 11 delta 11 error onlinli, derivire synl - 11. T.dot (12. deita) syno le.T.dot ( 11 delta) (4) print bothy and y.bat