Practice Gradient Descent (6.4.1) - Optimization Techniques

Practise this section

10 questions

Flashcard drill
4 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
4 questions · about 3 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What is the primary goal of Gradient Descent?
Show hintHide hint
Think about what we aim to solve in optimization.
Question 2.
What does the learning rate determine in Gradient Descent?
Show hintHide hint
How quickly do you want to move toward the solution?
3Question 3.
What does Gradient Descent aim to optimize?
- Maximize a function
- Minimize a function
- Both
Show hintHide hint
Think about the general goal of optimization.
4Question 4.
True or False: The learning rate must always be 1 for Gradient Descent.
- True
- False
Show hintHide hint
Does it have to be a specific number?
Question 5.
Given a quadratic function, derive the first few steps using Gradient Descent, assuming a learning rate of 0.1.
Show hintHide hint
Use the derivative to determine the gradient, then apply the update formula.
Question 6.
Discuss a scenario in which Stochastic Gradient Descent may provide better results than Batch Gradient Descent.
Show hintHide hint
What might happen if we never adjust based on individual data points?

6 more questions in this section. Enroll free to practise them all.