Check your understanding of this module before moving on.
?
0/3
Checkpoint quiz 3 questions
A quick check on this module's key ideas before you move on
Question 01
What is a loss function, in general?
B is correct. Every model in this course is, underneath its specific algorithm, searching for parameters that make some numeric definition of "wrong" as small as possible. That definition is the loss function.
Question 02
In gradient descent, what does the gradient tell you?
B is correct. The gradient points in the direction of steepest increase. Stepping the opposite way is, by definition, the fastest way to reduce the loss from where you currently stand.
Question 03
What happens if the learning rate is set too large?
B is correct. A step that's too big can jump past the minimum entirely, and if it's big enough, each subsequent step overshoots further in the other direction, growing instead of converging.