← All topics
Quiz: Gradient Descent: questions with answers
10 questions, each with the answer and a short explanation.
Take the timed quiz + get a certificate →- Q1. What does the gradient of the loss tell you?
- Q2. Which is the gradient descent update rule?
- Q3. What does this print? (code)
- Q4. The training loss becomes inf after a few epochs. What is the most likely fix?
- Q5. With learning rate 0.001, the loss was still about 130 after 500 epochs. Why?
- Q6. Why does feature scaling help gradient descent?
- Q7. What is one epoch?
- Q8. What does this print? (code)
- Q9. Which variant computes each gradient on a small random group of rows, such as 64?
- Q10. Why do the steps get smaller near the minimum even with a fixed learning rate?