Quiz Space

Deep Learning · Quiz 2 · 4 Aug 2024 · May 2024 term

Question 15: Consider a Convolutional Neural Network (CNN) architectu…

Question 15

+4 marksNumerical answer

Consider a Convolutional Neural Network (CNN) architecture for image classification with the following layers:
1. Convolutional layer with 6 filters of size 3 × 3, with a stride of 1 and no padding.
2. Max pooling layer with a pool size of 2 × 2 and a stride of 2.
3. Convolutional layer with 4 filters of size 4 × 4, with a stride of 1 and no padding.
4. Max pooling layer with a pool size of 2 × 2 and a stride of 2.
5. Fully connected layer with 20 neurons.
6. Output layer with 10 neurons (for 10 classes) using softmax activation.
If the input image size is 64 × 64 × 3, and the network has no bias term, how many parameters are there in the CNN?

Show answer

Correct answer: 16426

See the whole paperTake it as a mock test

Question 15 of 16 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 2 paper sat on 4 Aug 2024, in the May 2024 term (IIT M DEGREE AN EXAM QDB2 4 Aug 2024). It carries 4 marks.

More questions from this paper

  1. Q1Figure question
  2. Q2Which of the following statements accurately describes the behavior of the learning rate in the AdaGrad algorithm?
  3. Q3Figure question
  4. Q4What is the primary purpose of using cosine annealing with warm restarts in optimization algorithms?
  5. Q5How does dropout affect the behavior of the neural network during the inference phase?
  6. Q6Which of the following options correctly describes the effect of early stopping as a regularization technique in traini…
  7. Q7You are experimenting with L1 and L2 regularization techniques on a deep neural network trained on a moderately sized d…
  8. Q8What is the impact of using a sigmoid activation function on the gradients when the input to the neuron is a very large…
  9. Q9What is the derivative of the Leaky ReLU activation function with respect to its input?
  10. Q10Which of the following do not suffer from the vanishing gradient problem as well as the dead neurons problem?\ Sigmoid\…
  11. Q11Both sigmoid and tanh activation functions saturate:
  12. Q12You are working on a project where you aim to predict housing prices based on various features. You have split your dat…
  13. Q13Based on the above data, answer the given subquestions.
  14. Q14Pass a through the ReLU activation function and assign the output to h. ReLU(x) = \begin{cases} x, & if\ x \ge 0 \ 0, &…
  15. Q16Consider an intermediate feature map H obtained after applying convolution operation on the input X using kernel F. H =…