(Choose 2 answers)
A. (1)
B. (II)
C. (III)
D. (IV)
1
0
Suppose you have the following training set, and fit a logistic regression classifier ho(x) = g(0 + θιχι + 02χ2).
2
X2
0.5
1.5
1
y
0
1.5
1
1
1
+
0
0.5
2
3
1
0
Which of the following are true? Check all that apply.
(1) J(0) will be a convex function, so gradient descent should converge to the global minimum.
(II) Adding polynomial features (e.g., instead using ho(x) = 3(θα + θιχι + 02.02 + 03.x + 4x1x2 + 3x3)) could increase how well we can fit the training data.
(III) The positive and negative examples cannot be separated using a straight line. So, gradient descent will fail to converge.
1
E32
