Quiz Space

Introduction to Deep Learning and Generative AI · Quiz 2 · 12 Apr 2026 · January 2026 term

Question 15: Consider the following statements related to optimizatio…

Question 15

+2 marksOne or more correct options

Consider the following statements related to optimization in deep learning. Select all statements that are correct.

Select all that apply.

  1. A

    Step decay, exponential decay, and cosine decay are examples of learning rate scheduling techniques.

  2. B

    Accelerated gradient methods necessarily require the learning rate to decrease over time in order to converge.

  3. C

    Momentum-based methods can improve convergence speed even when the learning rate is kept constant.

  4. D

    Learning rate scheduling methods introduce memory of past gradients into the optimization process.

  5. E

    Learning rate scheduling and accelerated gradient methods can be used together.

Show answer

Correct answers

  • A

    Step decay, exponential decay, and cosine decay are examples of learning rate scheduling techniques.

  • C

    Momentum-based methods can improve convergence speed even when the learning rate is kept constant.

  • E

    Learning rate scheduling and accelerated gradient methods can be used together.

Video solution

The video solution to this question is being recorded and will play here. Until then, the answer key is above.

Question 15 of 20 in the IIT Madras BS Introduction to Deep Learning and Generative AI (Deep Learning and GenAI) Quiz 2 paper sat on 12 Apr 2026, in the January 2026 term (Introduction To Deep Learning And Generative Ai 06 Apr 26). It carries 2 marks.

More questions from this paper

  1. Q1Consider the following code:
  2. Q2Consider the following code: What is the spatial size of the output after applying the given pooling code?
  3. Q3Which of the following code snippets generates fake images from random noise for training a fully connected GAN network?
  4. Q4Consider the following code: What will be the final output of the code (z_biased)?
  5. Q5Consider the following architecture for a discriminator: In which of the following lines would you suggest code changes…
  6. Q6If Model A has cross-entropy loss = 2.0 and Model B has loss = 1.5, which model has lower perplexity?
  7. Q7Figure question
  8. Q8Consider the following code snippet:
  9. Q9Figure question
  10. Q10Figure question
  11. Q11You are designing a simple RNN to process sentences of length 10 words for next-word prediction in a chat application.\…
  12. Q12Consider the following real-valued functions defined on their natural domains. Select all functions that are convex ove…
  13. Q13In a GAN training loop, the following function is used before each backward pass: Suppose a GAN is trained and this fun…
  14. Q14During GAN training, the following code is used to update the discriminator: However the code doesnt work as intended. …
  15. Q16Consider the following reference sentence:\ Reference: machine learning is very fun Answer the subquestions based on th…
  16. Q17Consider the following reference sentence:\ Reference: machine learning is very fun Answer the subquestions based on th…
  17. Q18Consider the following PyTorch model: Answer the subquestions based on the given data. What is the total number of trai…
  18. Q19Consider the following PyTorch model: Answer the subquestions based on the given data.
  19. Q20What are the updated values of the weights after the first SGD step?