Deep Learning | NPTEL | Week 7 answers

This set of MCQ(multiple choice questions) focuses on the Deep Learning NPTEL Week 7 answers.

Course layout

Answers COMING SOON! Kindly Wait!

NOTE: You can check your answer immediately by clicking show answer button. This set of “Deep Learning NPTEL Week 7 answers ” contains 10 questions.

Now, start attempting the quiz.

Deep Learning NPTEL week 7 answers

Q1. Select the correct option.

a) Layer-by-layer autoencoder pretraining reduces GPU/CPU RAM requirements
b) Layer-by-layer autoencoder pretraining alleviates slow convergence
c) Layer-by-layer autoencoder pretraining followed by finetunin converges to more optimal parameters than End-to-End training of autoencoders
d) All of the above

Show Answer

Q2. Regularization of Contractive Autoencoders is imposed on

a) Jacobian matric of encoder activations with respect to the input
b) Weights
c) Inputs
d) Does not user regularization

Show Answer

Q3. Select true statements about KL Divergence

a) Measures distance between two probability distribution
b) Has range from 0 to 1
c) Is a symmetric, i.e. KL(P|Q) = KL(Q|P)
d) None of above

Show Answer

Deep Learning NPTEL week 7 answers

Q4. An overcomplete autoencoder generally learns identity function. How can we prevent those autoencoder from learning the identity function and learn some useful representations?

a) Stack autoencoder based layer-wise training
b) Train the autoencoder for large number of epochs in order to learn more useful representation
c) Add noise to the data and train to learn noise-free data from noisy data
d) It is not possible to train overcomplete autoencoder. It always converges to the identity function.

Show Answer

Q5. In which conditions, autoencoder has more powerful generalization than Prinicpal Components Analysis (PCA) while performing dimensionality reduction?

a) Undercomplete Linear Autoencoder
b) Overcomplete Linear Autoencoder
c) Undercomplete Non-linear Autoencoder
d) Overcomplete Non-linear Autoencoder

Show Answer

Q6. An autoencoder consists of 128 input neurons, 32 hidden neurons. If the network weights are represented using single precision floating point number (size = 4 bytes) then what will be size of weight matrix?

a) 33408 Bytes
b) 16704 Bytes
c) 8352 Bytes
d) 32768 Bytes

Show Answer

Deep Learning NPTEL week 7 answers

Q7. Which of the following is used to match template pattern in a signal

a) Cross Correlation
b) Convlution
c) Normalized cross correlation
d) None of the above

Show Answer

Deep Learning NPTEL week 7 answers

Q8. What is the role of sparsity constraint in a sparse autoencoder?

a) Control the number of active nodes in a hidden layer
b) Control the noise level in a hidden layer
c) Control the hidden layer length
d) Not related to sparse autoencoder

Show Answer

Q9. Which of the following is true about convolution?

a) Convolution is used to compute features from signal
b) Can be used to compute cross correlation between x(t) and y(t) if input signal x(t) is transformed to x(-t) and y(t) is used as filter
c) Both a and b
d) None of the above

Show Answer

Deep Learning NPTEL week 7 answers

Q10. Which of the following is an LTI/LSI system? y and x are output and input respectively

a) y = m X x and n X x
b) y = m X x + c
c) y = m X x – c
d) y = m X x²

Show Answer

Deep Learning NPTEL week 7 answers

Deep Learning NPTEL Week 7 answers

Ans1. a)

Ans2. d)

Ans3. b)

Ans4. c)

Ans5. d)

Ans6. a)

Ans7. c)

Ans8. b)

Ans9. a)

Ans10. c)

---

<< Prev: Deep Learning NPTEL Week 6 Answers

>> Next: Deep Learning NPTEL Week 8 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.