🎙 Free live masterclass · Sun, 29 Nov, 7:00 pm IST · Java Full Stack roadmap Register free →
Skills101
← 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 →
  1. Q1. What does the gradient of the loss tell you?
  2. Q2. Which is the gradient descent update rule?
  3. Q3. What does this print? (code)
  4. Q4. The training loss becomes inf after a few epochs. What is the most likely fix?
  5. Q5. With learning rate 0.001, the loss was still about 130 after 500 epochs. Why?
  6. Q6. Why does feature scaling help gradient descent?
  7. Q7. What is one epoch?
  8. Q8. What does this print? (code)
  9. Q9. Which variant computes each gradient on a small random group of rows, such as 64?
  10. Q10. Why do the steps get smaller near the minimum even with a fixed learning rate?