atiato (15) [Avatar] Offline
#1
In the Listing 4.7 Using TensorFlow for multidimensional logistic regression

Why the below is negative sign and why it is not tf.sigmoid?

z = sigmoid(-x2_test*w_val[2] - x1_test*w_val[1] - w_val[0])

Could you explain How you generate fake data as in the normal distribution below :

x1_label1 = np.random.normal(3, 1, 1000)
x2_label1 = np.random.normal(2, 1, 1000)
x1_label2 = np.random.normal(7, 1, 1000)
x2_label2 = np.random.normal(6, 1, 1000)

thanks,
Omar Atia