Quiz Space

Deep Learning for Computer Vision · Quiz 1 · 23 Feb 2025 · January 2025 term

Deep Learning for Computer Vision Quiz 1 23 Feb 2025 — Question 19

Question 19

+2 marksOne correct option

Which of the following statements are True?

  1. A

    Vanilla Gradient Descent converges faster than Momentum-based GD.

  2. B

    Momentum based GD oscillates around minima before convergence.

  3. C

    Noise in Stochastic Gradient descent weight updates – can lead to faster convergence.

  4. D

    None of these

Show answer

Correct answer

  • B

    Momentum based GD oscillates around minima before convergence.

See the whole paperTake it as a mock test

Question 19 of 36 in the IIT Madras BS Deep Learning for Computer Vision (Deep Learning for Computer Vision) Quiz 1 paper sat on 23 Feb 2025, in the January 2025 term (IIT M DEGREE AN EXAM QDB2 23 Feb 2025). It carries 2 marks.

This question was also asked in

More questions from this paper

  1. Q1Consider the following numpy array \text{arr} = \begin{bmatrix} 0 & 1 \ 2 & 3 \ 4 & 5 \end{bmatrix} Now consider the fo…
  2. Q2Consider the following numpy array \text{arr} = \begin{bmatrix} 0 & 1 \ 2 & 3 \ 4 & 5 \end{bmatrix} Now consider the fo…
  3. Q3Consider the grayscale image shown below: \begin{bmatrix} 20 & 30 & 25 & 30 & 40 \ 45 & 10 & 40 & 35 & 20 \ 15 & 20 & 3…
  4. Q4Figure question
  5. Q5What is the size of the feature map after applying two successive convolution operations with given parameters? Image s…
  6. Q6Let an input to a convolutional layer in a CNN have size Df × Df × M where Df = 32 and M = 100, and output feature map …
  7. Q7Figure question
  8. Q8Given is a 3 \times 3 8-bit grayscale image: \begin{bmatrix} 50 & 70 & 120 \ 90 & 30 & 80 \ 40 & 60 & 110 \end{bmatrix}…
  9. Q9Which of the following statements is True ?
  10. Q10Figure question
  11. Q11Identify the correct sequence of steps in a Canny edge detection pipeline. Steps are listed below: 1. Compute gradient …
  12. Q12Identify the correct sequence of steps in Scale Invariant Feature Transform (SIFT) method. Steps listed below:\ Keypoin…
  13. Q13Figure question
  14. Q14Suppose we have a codebook of 2048 SIFT visual words. We extract 1000 SIFT descriptors (SIFT is a 128-dimensional featu…
  15. Q15Match the derivative of activation functions f(x) with their counterparts on the right column accordingly. | 1) Leaky R…
  16. Q16Consider a Convolutional Neural Network which processes an RGB image. It has 128 kernels each of spatial dimension 5 × …
  17. Q17Consider the following two statements. Which of the following statements are true?\ (a) Convolution operator is both co…
  18. Q18A 3x3 kernel generates an output image of dimension 20x20 after convolution. The (approximate) number of computations p…
  19. Q20Figure question
  20. Q21Which of the following statements is false?
  21. Q22Which of the following statements are false?
  22. Q23Figure question
  23. Q24Certain 2D kernel K can be decomposed into two 1D kernels (v and h) to reduce the computation cost such as K = vh^\top.…
  24. Q25Which of the following statements are true? (Select all that apply)
  25. Q26Which of the following are true? (Select all that apply)
  26. Q27Enter the correct answer for blank (a) \ NOTE: Enter the exact answer without any extra space in the beginning or at th…
  27. Q28Enter the correct answer for blank (b) \ NOTE: Enter the exact answer without any extra space in the beginning or at th…
  28. Q29Enter the correct answer for blank (a) \ NOTE: Enter the exact answer without any extra space in the beginning or at th…
  29. Q30Enter the correct answer for blank (b) \ NOTE: Enter the exact answer without any extra space in the beginning or at th…
  30. Q31a11=
  31. Q32a12=
  32. Q33a21=
  33. Q34a22=
  34. Q35Figure question
  35. Q36Figure question