This set of MCQ(multiple choice questions) focuses on the **Deep Learning Week 8 answers**

### Course layout

*Answers COMING SOON! Kindly Wait!*

** Week 1: Assignment Answers**Week 3: Assignment Answers

Week 2: Assignment Answers

**Week 4:**

Week 5:

Week 6:

Week 7:

Week 8:

Week 9:

Week 10:

Week 11:

Week 12:

**Assignment Answers**Week 5:

**Assignment Answers**Week 6:

**Assignment Answers**Week 7:

**Assignment Answers**Week 8:

**Assignment Answers**Week 9:

**Assignment Answers**Week 10:

**Assignment Answers**Week 11:

**Assignment Answers**Week 12:

**Assignment Answers**

**NOTE:** You can check your answer immediately by clicking show answer button. This set of** “ Deep Learning Week 8 answers **” contains 10 questions.

Now, start attempting the quiz.

### Deep Learning week 8 answers

**Q1.** Which of the following best describes the concept of saturation in deep learning?

a) When the activation function output approaches either 0 or 1 and the gradient is close to zero.

b) When the activation function output is very small and the gradient is close to zero

c) When the activation function output is very large and the gradient is close to zero.

d) None of the above

Answer: a), b), c)

**Q2.** Which of the following methods can help to avoid saturation in deep learning?

a) Using a different activation function

b) Increasing the learning rate

c) Increasing the model complexity

d) All of the above

Answer: a) Using a different activation function

**Q3.** Which of the following is true about the role of unsupervised pre-training in deep learning?

a) It is used to replace the need for labeled data

b) It is used to initialize the weights of a deep neural network

c) It is used to fine-tune a pre-trained model

d) It is only useful for small datasets

Answer: b) It is used to initialize the weights of a deep neural network

**Q4.** Which of the following is an advantage of unsupervised pre-training in deep learning?

a) It helps in reducing overfitting

b) Pre-trained models converge faster

c) It improves the accuracy of the model

d) It requires fewer computational resources

Answer: a), b), c)

**Q5.** What is the main cuase of the Dead ReLU problem in deep learning?

a) High variance

b) High negative bias

c) Overfitting

d) Underfitting

Answer: b) High negative bias

**Q6.** How can you tell if your network is suffering from the Dead ReLU problem?

a) The loss function is not decreasing during training

b) The accuracy of the network is not improving

c) A large number of neurons have zero output

d) The network is overfitting to the training data

Answer: c) A large number of neurons have zero output

**Q7.** What is the mathematical expression for the ReLU activation function?

a) f(x) = x if x < 0, 0 otherwise

b) f(x) = 0 if x > 0, x otherwise

c) f(x) = max(0, x)

d) f(x) = min(0, x)

Answer: c) f(x) = max(0, x)

**Q8.** What is the main cause of the symmetry breaking problem in deep learning?

a) High variance

b) High bias

c) Overfitting

d) Equal initialization of weights

Answer: d) Equal initialization of weights

**Q9.** What is the purpose of Batch Normalization in Deep learning?

a) To improve the generalization of the model

b) To reduce overfitting

c) To reduce bias in the model

d) To ensure that the distribution of the inputs at different layers doesn’t change

Answer: d) To ensure that the distribution of the inputs at different layers doesn’t change

**Q10.** In Batch Normalization, which parameter is learned during training?

a) Mean

b) Variance

c) *𝛾*

d) ε** **

Answer: c) 𝛾

**Deep Learning** Week 8 answers

**Q1.** Which of the following is false about CNN?

a) Output should be flattened before feeding it to a fully connected layer

b) There can be only 1 fully connected layer in CNN

c) We can use as many convolutional layers in CNN

d) None of the above

**Answer:** b)

**Q2.** The input image has been converted into a matrix of size 64 x 64 and a kernel/filter of size 5×5 with a stride of 1 and no padding. What will be the size of the convoluted matrix?

a) 5×5

b) 59×59

c) 64×64

d) 60×60

**Answer:** d)

**Q3.** Filter size of 3×3 is convolved with matrix of size 4×4 (stride=1). What will be the size of output matrix if valid padding is applied:

a) 4×4

b) 3×3

c) 2×2

d) 1×1

**Answer:** a)

**Q4.** Let us consider a Convolutional Neural Network having three different convolutional layers in its architecture as:

Layer-1: Filter Size – 3 x 3, Number of Filters – 10, Stride – 1, Padding – 0

Layer 2: Filter Size – 5 x 5, Number of Filters – 20, Stride – 2, Padding – 0

Layer 3: Filter Size – 5 x 5, Number of Filters – 40, Stride – 2, Padding – 0

Layer 3 of the above network is followed by a fully connected layer. If we give a 3-D image input of dimension 39 X 39 to the network, then which of the following is the input dimension of the fully connected layer.

a) 1960

b) 2200

c) 4563

d) 13690

**Answer:** a)

**Q5.** Suppose you have 40 convolutional kernel of size 3×3 with no padding and stride 1 in the first layer of a convolutional neural network. You pass an input of dimension 1024x1024x3 through this layer. What are the dimensions of the data which the next layer will receive?

a) 1024x1024x40

b) 1022x1022x40

c) 1021x1021x40

d) 1022x1022x3

**Answer:** b)

**Q6.** Consider a CNN model which aims at classifying an image as either a rose, or a marigold, or a lily or an orchid(consider the test image can have only 1 of the classes at a time). The last(fully-connected) layer of the CNN outputs a vector of logits, L, that is passed through a _________ activation that transforms the logits into probabilities, P. These probabilities are the model predictions for each of the 4 classes. Fill in the blanks with the appropriate option.

Fill in the blanks with the appropriate option.

a) Leaky ReLU

b) Tanh

c) ReLU

d) Softmax

**Answer:** d)

**Q7.** Suppose your input is a 300 by 300 color(RGB) image, and you use a convolutional layer with 100 filters that are each 5×5. How many parameters does this hidden layer have(without bias)

a) 2501

b) 2600

c) 7500

d) 7600

**Answer:** c)

**Q8.** Which of the following activation functions can lead to vanishing gradients?

a) ReLU

b) Sigmoid

c) Leaky ReLU

d) None of the above

**Answer:** b)

**Q9.** Statement 1: Residual networks can be a solution for vanishing gradient problem

Statement 2: Residual networks provide residual connections straight to earlier layers

Statement 3: Residual networks can never be a solution for vanishing gradient problem

Which of the following option is correct?

a) Statement 2 is correct

b) Statement 3 is correct

c) Both Statement 1 and Statement 2 are correct

d) Both Statement 2 and Statement 3 are correct

**Answer:** d)

**Q10.** Input to SoftMax activation function is [0.5, 0.5, 1]. What will be the output?

a) [0.28, 0.28, 0.44]

b) [0.022, 0.956, 0.022]

c) [0.045, 0.910, 0.045]

d) [0.42, 0.42, 0.16]

**Answer:** a)

**<< Prev: Deep Learning NPTEL Week 7 Answers**

**>> Next: Deep Learning NPTEL Week 9 Answers**

Disclaimer: Quizermaina doesn’t claim these answers to be 100% correct. Use these answers just for your reference. Always submit your assignment as per the best of your knowledge.

*For discussion about any question, join the below comment section. And get the solution of your query.* Also, try to share your thoughts about the topics covered in this particular quiz.