NPTEL Deep Learning - IIT Ropar Week Assignment Answers 2024

NPTEL Deep Learning – IIT Ropar Week Assignment Answers 2024

1. Consider an input image of size 1000×1000×10 where 10 refers to the number of channels (Such images do exist!). Suppose we want to apply a convolution operation on the entire image by sliding a kernel of size 1×1×d. What should be the depth d of the kernel?

Answer :- For Answers Click Here

2. For the same input image in Q1, suppose that we apply the following kernels of differing sizes.

K₁:3×3
K₂:7×7
K₃:17×17
K₄:41×41

Assume that stride s=1 and no zero padding. Among all these kernels which one shrinks the output dimensions the most?

K₁
K₂
K₃
K₄

Answer :- For Answers Click Here

3. Which of the following statements about CNN is (are) true?

CNN is a feed-forward network
Weight sharing helps CNN layers to reduce the number of parameters
CNN is suitable only for natural images
The shape of the input to the CNN network should be square

Answer :- For Answers Click Here

4. Consider an input image of size 100×100×1. Suppose that we used kernel of size 3×3, zero padding P=1 and stride value S=3. What will be the output dimension?

Answer :-

5. Consider an input image of size 100×100×3. Suppose that we use 10 kernels (filters) each of size 1×1
, zero padding P=1 and stride value S=2. How many parameters are there? (assume no bias terms)

Answer :-

6. Which statement is true about the size of filters in CNNs?

The size of the filter does not affect the features it captures.
The size of the filter only affects the computation time.
Larger filters capture more global features.
Smaller filters capture more local features.

Answer :- For Answers Click Here

7. What is the motivation behind using multiple filters in one Convolution layer?

Reduced complexity of the network
Reduced size of the convolved image
Insufficient information
Each filter captures some feature of the image separately

Answer :-

8. Which of the following architectures has the highest no of layers?

AlexNet
GoogleNet
ResNet
VGG

Answer :-

9. What is the purpose of guided backpropagation in CNNs?

To train the CNN to improve its accuracy on a given task.
To reduce the size of the input images in order to speed up computation.
To visualize which pixels in an image are most important for a particular class prediction.
None of the above.

Answer :-

10. Which of the following statements is true regarding the occlusion experiment in a CNN?

It is a technique used to prevent overfitting in deep learning models.
It is used to increase the number of filters in a convolutional layer.
It is used to determine the importance of each feature map in the output of the network.
It involves masking a portion of the input image with a patch of zeroes.