Quiz Space

Deep Learning · Quiz 2 · 3 Aug 2025 · May 2025 term

Question 1: Consider four training experiments, each involving a neur…

Question 1

+3 marksOne correct option

Consider four training experiments, each involving a neural network trained on the same dataset for 50 epochs using gradient descent. The loss curves for these models are shown below. The model obtained at the end of 50 epochs is retained in each of the four cases. The solid curve is the training loss and the dashed curve is the validation loss.

Now consider these four statements.
(A) Learning rate used is too high
(B) Low bias and high variance
(C) Low bias and low variance
(D) High bias and low variance
Choose the most appropriate pairing of models with the statements.

  1. A
  2. B
  3. C
  4. D
Show answer

Correct answer

  • A

Question 1 of 16 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 2 paper sat on 3 Aug 2025, in the May 2025 term (IIT M DEGREE AN EXAM QDB2 03 Aug 2025). It carries 3 marks.

More questions from this paper

  1. Q2Which of the following optimizers use an adaptive learning rate?
  2. Q3An autoencoder is a feedforward neural network in which the input and the output layer have the same number of neurons.…
  3. Q4Figure question
  4. Q5Which of these is the shape of the output volume after the convolution operation?
  5. Q6Find the total number of parameters associated with the convolutional layer.
  6. Q7If the input volume to the convolutional layer is 128 × 128 × 8, would the number of parameters associated with the con…
  7. Q8Consider an ML model for which the un-regularized loss on some dataset D as a function of parameter vector w = (w_1, w_…
  8. Q9Consider an ML model for which the un-regularized loss on some dataset D as a function of parameter vector w = (w_1, w_…
  9. Q10Consider an ML model for which the un-regularized loss on some dataset D as a function of parameter vector w = (w_1, w_…
  10. Q11Based on the above data, answer the given subquestions.
  11. Q12Based on the above data, answer the given subquestions.
  12. Q13Based on the above data, answer the given subquestions.
  13. Q14For a regression problem, consider an image X of size 4×4 and true label y that is passed through a toy convolutional n…
  14. Q15For a regression problem, consider an image X of size 4×4 and true label y that is passed through a toy convolutional n…
  15. Q16For a regression problem, consider an image X of size 4×4 and true label y that is passed through a toy convolutional n…