Quiz Space

Introduction to Deep Learning and Generative AI · Quiz 2 · 23 Nov 2025 · September 2025 term

Question 6: The Momentum optimizer helps overcome which limitation of…

Question 6

+1 markOne correct option

The Momentum optimizer helps overcome which limitation of vanilla Gradient Descent?

  1. A

    Slow convergence near the minimum due to large learning rate.

  2. B

    Zig-zag oscillations in narrow valleys due to gradient directions changing frequently.

  3. C

    Vanishing gradients caused by activation functions.

  4. D

    Overfitting due to excessive updates.

Show answer

Correct answer

  • B

    Zig-zag oscillations in narrow valleys due to gradient directions changing frequently.

See the whole paperTake it as a mock test

Question 6 of 25 in the IIT Madras BS Introduction to Deep Learning and Generative AI (Deep Learning and GenAI) Quiz 2 paper sat on 23 Nov 2025, in the September 2025 term (IIT M DIPLOMA AN EXAM QDD2 23 Nov 2025 NEW). It carries 1 mark.

More questions from this paper

  1. Q1You have a tensor x = torch.tensor([1, 2, 3, 4]). You perform And What will be the shapes of stacked_x_dim0 and stacked…
  2. Q2You have a PyTorch tensor residing on the GPU. You then attempt to convert it directly to a NumPy array using What will…
  3. Q3The Huber Loss function is introduced as a robust alternative to Mean Squared Error (MSE) and Mean Absolute Error (MAE)…
  4. Q4A deep learning model contains a stack of three consecutive 3x3 convolutional layers, each with a stride of 1and suffic…
  5. Q5Figure question
  6. Q7Consider the RMSProp optimizer update rule: v_t = \beta v_{t-1} + (1 - \beta)(\nabla w_t)^2 The algorithm runs for 10 i…
  7. Q8You are given two loss functions. Your task is to identify their nature using the second derivative test. Function A: A…
  8. Q9What happens if the latent space in a GAN has too few dimensions for the task complexity?
  9. Q10At Nash Equilibrium in a perfectly trained GAN, what is the expected output of the discriminator D(G(z)) for a generate…
  10. Q11A student is trying to write the Generator training loop and is confused about the order of operations. Their code is: …
  11. Q12You've been training your GAN for 100 epochs. You notice two things: The Generator loss (g_loss) is very low and stable…
  12. Q13Figure question
  13. Q14Figure question
  14. Q15Figure question
  15. Q16Consider that the following paragraph is used as the input to train a sequence language model: "this is a great sunny d…
  16. Q17Figure question
  17. Q18You are performing Beam Search with K=2 to generate a sequence. Step 1: The model predicts probabilities for the first …
  18. Q19Figure question
  19. Q20Figure question
  20. Q21Given the update rule for Adagrad \begin{aligned} v_t &= v_{t-1} + (\nabla w_t)^2 \ w_{t+1} &= w_t - \frac{\eta}{\sqrt{…
  21. Q22In an LSTM (Long Short-Term Memory) network, which pair of components correctly represents the short-term and long-term…
  22. Q23The LSTM (Long Short-Term Memory) network uses several gates to control information flow. Here are the key equations wi…
  23. Q24You are training an RNN-based text classification model with the following three sequences: Under which training scenar…
  24. Q25Consider the following modified implementation of an RNN. What will be the percentage reduction in the rnn parameters d…