Quiz Space

Introduction to Deep Learning and Generative AI · Quiz 2 · 16 Aug 2026 · May 2026 term

Question 16: Select all statements that are TRUE regarding the mechan…

Question 16

+3 marksOne or more correct options

Select all statements that are TRUE regarding the mechanics of Adagrad and RMSProp.

Select all that apply.

  1. A

    Assuming a constant base learning rate, Adagrad's squared-gradient accumulator only grows (or stays the same), meaning a parameter's effective learning rate can never increase over time.

  2. B

    In RMSProp, a parameter's effective learning rate can actually increase again if it starts receiving much smaller gradients than it did previously.

  3. C

    For sparse features (which rarely receive non-zero gradients), Adagrad forces the effective learning rate to decay much more slowly compared to frequently updated dense features.

  4. D

    Over a very long training run, RMSProp's accumulator eventually converges to the total sum of all squared gradients seen during training.

  5. E

    Changing Adagrad's infinite cumulative sum into an exponentially decaying average is exactly the modification that creates RMSProp and solves the vanishing learning rate problem.

Show answer

Correct answers

  • A

    Assuming a constant base learning rate, Adagrad's squared-gradient accumulator only grows (or stays the same), meaning a parameter's effective learning rate can never increase over time.

  • B

    In RMSProp, a parameter's effective learning rate can actually increase again if it starts receiving much smaller gradients than it did previously.

  • C

    For sparse features (which rarely receive non-zero gradients), Adagrad forces the effective learning rate to decay much more slowly compared to frequently updated dense features.

  • E

    Changing Adagrad's infinite cumulative sum into an exponentially decaying average is exactly the modification that creates RMSProp and solves the vanishing learning rate problem.

See the whole paperTake it as a mock test

Question 16 of 19 in the IIT Madras BS Introduction to Deep Learning and Generative AI (Deep Learning and GenAI) Quiz 2 paper sat on 16 Aug 2026, in the May 2026 term (Introduction To Deep Learning And Generative Ai 14 Aug 26). It carries 3 marks.

More questions from this paper

  1. Q1Consider the following code snippet: Based on the standard normalization technique for a single-channel grayscale image…
  2. Q2Suppose during training Epoch 1 D(real)=0.90 D(fake)=0.10 Later Epoch 20 D(real)=0.999 D(fake)=0.0001\ What problem is …
  3. Q3Let D(x) denote the discriminator's output. Which of the following represents the most desirable discriminator output d…
  4. Q4What is the output of the following code snippet?
  5. Q5Figure question
  6. Q6Consider the following implementation of a RNN: What is the output of the print statements?
  7. Q7Which of the following options is correct regarding the standard encoder-decoder architecture?
  8. Q8Figure question
  9. Q9Which of the following statements must be true?
  10. Q10A GAN is trained on images preprocessed using the following PyTorch transformation: Which of the following activation f…
  11. Q11Select the correct statements from the following:
  12. Q12Which of the following increase(s) the output size?
  13. Q13Select all statements that are TRUE.
  14. Q14Figure question
  15. Q15Figure question
  16. Q17Calculate the total number of parameters in the RNN implemented in the following code:
  17. Q18Figure question
  18. Q19Figure question