NPTEL Deep Learning – IIT Ropar Week 4 Assignment Answers 2024

Join Our WhatsApp Group Join Now
Join Us On Telegram Join Now

NPTEL Deep Learning – IIT Ropar Week 4 Assignment Answers 2024

1. We have following functions x3, ln (x), ex, x and 4. Which of the following functions has the steepest slope at x=1?

  • x3
  • ln(x)
  • ex
  • 4
Answer :- For Answer Click Here 

2. Which of the following represents the contour plot of the function f(x,y) =x2−y2?

Answer :- For Answer Click Here 

3. Choose the correct options for the given gradient descent update rule ωt+1=ωt−η∇ω(η is the learning rate)

  • The weight update is tiny at a gentle loss surface
  • The weight update is tiny at a steep loss surface
  • The weight update is large at a steep loss surface
  • The weight update is large at a gentle loss surface
Answer :- For Answer Click Here 

4. Which of the following algorithms will result in more oscillations of the parameter during the training process of the neural network?

  • Stochastic gradient descent
  • Mini batch gradient descent
  • Batch gradient descent
  • Batch NAG
Answer :- 

5. Which of the following are among the disadvantages of Adagrad?

  • It doesn’t work well for the Sparse matrix.
  • It usually goes past the minima.
  • It gets stuck before reaching the minima.
  • Weight updates are very small at the initial stages of the algorithm.
Answer :- 

6. Which of the following is a variant of gradient descent that uses an estimate of the next gradient to update the current position of the parameters?

  • Momentum optimization
  • Stochastic gradient descent
  • Nesterov accelerated gradient descent
  • Adagrad
Answer :- For Answer Click Here 

7. Consider a gradient profile ∇W=[1,0.9,0.6,0.01,0.1,0.2,0.5,0.55,0.56].
Assume v−1=0,ϵ=0,β=0.9 and the learning rate is η−1=0.1. Suppose that we use the Adagrad algorithm then what is the value of η6=η/sqrt(vt+ϵ)?

  • 0.03
  • 0.06
  • 0.08
  • 0.006
Answer :- 

8. Which of the following can help avoid getting stuck in a poor local minimum while training a deep neural network?

  • Using a smaller learning rate.
  • Using a smaller batch size.
  • Using a shallow neural network instead.
  • None of the above.
Answer :- 

9. What are the two main components of the ADAM optimizer?

  • Momentum and learning rate.
  • Gradient magnitude and previous gradient.
  • Exponential weighted moving average and gradient variance.
  • Learning rate and a regularization term.
Answer :- 

10. What is the role of activation functions in deep learning?

  • Activation functions transform the output of a neuron into a non-linear function, allowing the network to learn complex patterns.
  • Activation functions make the network faster by reducing the number of iterations needed for training.
  • Activation functions are used to normalize the input data.
  • Activation functions are used to compute the loss function.
Answer :- For Answer Click Here