Loading question session…
11 questions
What is the primary purpose of gradient descent in machine learning?
Which of the following best describes the 'learning rate' in gradient descent?
Which of these scenarios can cause gradient descent to converge slowly or not at all?
Gradient descent is used to find the maximum value of a function.
If the learning rate is too small, gradient descent will take a very long time to converge.
Batch gradient descent uses the entire training dataset to compute the gradient at each step.
In your own words, explain why gradient descent is important in machine learning.
Press “Enter” to evaluate answer, “Shift+Enter” to add a new line
What might happen if you choose a learning rate that is too high during gradient descent?
Press “Enter” to evaluate answer, “Shift+Enter” to add a new line
Describe a method to improve gradient descent convergence when the loss function has many local minima.
Press “Enter” to evaluate answer, “Shift+Enter” to add a new line
Which of the following best illustrates the concept of a 'gradient' in gradient descent?
Gradient descent can always guarantee finding the global minimum of a convex function.