NPTEL Deep Learning – IIT Ropar Week 4 Assignment Answers 2025

By /

NPTEL Deep Learning – IIT Ropar Week 4 Assignment Answers 2025

1. Using the Adam optimizer with β1=0.9, β2=0.999, and ϵ=10−8, what would be the bias-corrected first moment estimate after the first update if the initial gradient is 4?

  • 0.4
  • 4.0
  • 3.6
  • 0.44
Answer :-  For Answers Click Here

2. In a mini-batch gradient descent algorithm, if the total number of training samples is 50,000 and the batch size is 100, how many iterations are required to complete 10 epochs?

  • 5,000
  • 50,000
  • 500
  • 5
Answer :-

3. In a stochastic gradient descent algorithm, the learning rate starts at 0.1 and decays exponentially with a decay rate of 0.1 per epoch. What will be the learning rate after 5 epochs?

Answer :-

4. In the context of Adam optimizer, what is the purpose of bias correction?

  • To prevent overfitting
  • To speed up convergence
  • To correct for the bias in the estimates of first and second moments
  • To adjust the learning rate
Answer :-

5. The figure below shows the contours of a surface.

Suppose that a man walks, from -1 to +1, on both the horizontal (x) axis and the vertical (y) axis. The statement that the man would have seen the slope change rapidly along the x-axis than the y-axis is,

  • True
  • False
  • Cannot say
Answer :-

6. What is the primary benefit of using Adagrad compared to other optimization algorithms?

  • It converges faster than other optimization algorithms.
  • It is more memory-efficient than other optimization algorithms.
  • It is less sensitive to the choice of hyperparameters(learning rate).
  • It is less likely to get stuck in local optima than other optimization algorithms.
Answer :-  For Answers Click Here

7. What are the benefits of using stochastic gradient descent compared to vanilla gradient descent?

  • SGD converges more quickly than vanilla gradient descent.
  • SGD is computationally efficient for large datasets.
  • SGD theoretically guarantees that the descent direction is optimal.
  • SGD experiences less oscillation compared to vanilla gradient descent.
Answer :-

8. 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 :-

9. What is the advantage of using mini-batch gradient descent over batch gradient descent?

  • Mini-batch gradient descent is more computationally efficient than batch gradient descent.
  • Mini-batch gradient descent leads to a more accurate estimate of the gradient than batch gradient descent.
  • Mini batch gradient descent gives us a better solution.
  • Mini-batch gradient descent can converge faster than batch gradient descent.
Answer :-

10. In the Nesterov Accelerated Gradient (NAG) algorithm, the gradient is computed at:

  • The current position
  • A “look-ahead” position
  • The previous position
  • The average of current and previous positions
Answer :- For Answers Click Here

Related Posts

Scroll to Top