Quiz Space

Deep Learning · Quiz 2 · 1 Dec 2024 · September 2024 term

Question 15: Which of the following statements is/are true about a CO…

Question 15

+2 marksOne or more correct options

Consider an input image of shape 10×10 with 3 channels of R-G-B, is processed using one of the following neural architectures:
• Fully-connected layer (FC) with 2 neurons (Note: The input volume is “flattened” into a column vector before being fed into the layer.)
• Convolutional layer (CONV) with three filters of size 2 × 2, a stride of 2 is used, and no padding is applied.
Based on the above data answer the given subquestions.

Which of the following statements is/are true about a CONV layer?

Select all that apply.

  1. A

    The total number of parameters depends on the depth of the input.

  2. B

    The total number of parameters depends on the padding.

  3. C

    The total number of parameters depends on the number of filters (kernel).

  4. D

    The total number of parameters depends on the stride.

Show answer

Correct answers

  • A

    The total number of parameters depends on the depth of the input.

  • C

    The total number of parameters depends on the number of filters (kernel).

See the whole paperTake it as a mock test

Question 15 of 23 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 2 paper sat on 1 Dec 2024, in the September 2024 term (IIT M DEGREE AN EXAM QDB2 01 Dec 2024). It carries 2 marks.

More questions from this paper

  1. Q1Given a quadratic loss function L(w) = w^2, where w represents the model parameter, you are using the AdaGrad optimizer…
  2. Q2Given a quadratic loss function L(w) = w^2, where w represents the model parameter, you are using the AdaGrad optimizer…
  3. Q3Given a quadratic loss function L(w) = w^2, where w represents the model parameter, you are using the AdaGrad optimizer…
  4. Q4Which of the following optimization algorithms adapts the learning rate based on the current gradient and the history o…
  5. Q5Which of the following are regularization technique(S)?
  6. Q6Which of the following activation function(s) is (are) prone to vanishing gradient problem?
  7. Q7Which optimization algorithm combines the advantages of RM-Sprop and momentum?
  8. Q8What is the key reason for the development of adaptive optimization algorithms like RMSprop and Adam?
  9. Q9What is the derivative of the Leaky ReLU activation function with respect to its input?
  10. Q10Which of the following options represents the correct ordering in terms of the bias of the models illustrated in the im…
  11. Q11Which of the following is a common form of regularization that involves adding a penalty proportional to the square of …
  12. Q12Figure question
  13. Q13Which architecture has fewer parameters (CONV or FC)?
  14. Q14What is the difference in the number of trainable parameters between these two neural architectures?
  15. Q16Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…
  16. Q17Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…
  17. Q18Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…
  18. Q19Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…
  19. Q20Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…
  20. Q21Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…
  21. Q22Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…
  22. Q23Consider the below deep neural architecture, being applied on an image of size 128 × 128 with 3 channels of R-G-B. Assu…