Coursera 吴恩达 Machine Learning 课程 week 5 quiz

1.Question 1

You are training a three layer neural network and would like to use backpropagation to compute the gradient of the cost function. In the backpropagation algorithm, one of the steps is to update

for every i, ji,j. Which of the following is a correct vectorization of this step?

Coursera 吴恩达 Machine Learning 课程 week 5 quiz

Correct

This version is correct, as it takes the "outer product" of the two vectors \delta^{(3)}δ(3) and a^{(2)}a(2) which is a matrix such that the (i,j)(i,j)-th entry is \delta^{(3)}_i * (a^{(2)})_jδi(3)∗(a(2))j as desired.

2.Question 2

Suppose ???????????????????????? is a 5x3 matrix, and ???????????????????????? is a 4x6 matrix. You set ????????????????????????????????=[????????????????????????(:);????????????????????????(:)]. Which of the following correctly recovers ?????????????????????????

????????????????????????????(????????????????????????????????(????????:????????),????,????)

Incorrect

Since Octave indexing starts at 1, ????????????????????????????????(????????:????????) starts at the last element of ????????????????????????instead of the first element of ????????????????????????.

0 / 1 point

3.Question 3

Coursera 吴恩达 Machine Learning 课程 week 5 quiz

4.Question 4

Coursera 吴恩达 Machine Learning 课程 week 5 quiz

5.Question 5

Coursera 吴恩达 Machine Learning 课程 week 5 quiz