Quiz Space

Introduction to Deep Learning and Generative AI · Quiz 1 · 19 Jul 2026 · May 2026 term

Question 5: A student is training a neural network for regression pro…

Question 5

+3 marksOne correct option

A student is training a neural network for regression problem with a sigmoid activation at the output layer to predict the continuous value between 0 and 1. The true mathematical error term for Mean Squared Error (MSE) loss is . However, due to a coding mistake, the student implements the error term for Binary Cross- Entropy (BCE) loss instead, calculating it as . Assuming the network has not yet reached zero error ( ), which of the following correctly describes the relationship between the implemented and the true ?

  1. A

    The student's equals the true because the error term always holds regardless of loss function.

  2. B

    The student's is always at least 4 times larger in magnitude than true .

  3. C

    The student's is smaller than the true because sigmoid squashes the gradient.

  4. D

    The student's equals the true only when , since is maximum there and cancels with the MSE factor.

Show answer

Correct answer

  • B

    The student's is always at least 4 times larger in magnitude than true .

Video solution

The video solution to this question is being recorded and will play here. Until then, the answer key is above.

See the whole paperTake it as a mock test

Question 5 of 20 in the IIT Madras BS Introduction to Deep Learning and Generative AI (Deep Learning and GenAI) Quiz 1 paper sat on 19 Jul 2026, in the May 2026 term (Introduction To Deep Learning And Generative Ai 16 Jul 26). It carries 3 marks.

More questions from this paper

  1. Q1Consider the following data point and weight vector in a simple single layer neural network. (Assume that there is no b…
  2. Q2A BatchNorm layer is applied to the output of a convolutional layer. The output feature map has dimensions: where: 32 =…
  3. Q3Consider a McCulloch-Pitts (MP) neuron with binary inputs, unit positive weights, and no inhibitory connections. Given …
  4. Q4Consider the following pytorch code: What is the output of the above code?
  5. Q6An input image of size 32×32 is passed through a CNN containing three convolution layers: • Conv1: 3x3, stride 1 • Conv…
  6. Q7For a convolution layer, suppose the input feature map has size 28x28x64. A 1x1 convolution with 32 filters is applied …
  7. Q8A convolution operation is applied to an input image of size 64x64 using a single 3x3 filter. The convolution uses: Ker…
  8. Q9Consider the following PyTorch convolutional layer: How many total learnable parameters (including biases) does this la…
  9. Q10Consider the following image preprocessing pipeline: Which of the following statements is correct about the above prepr…
  10. Q11A perceptron in 2D is defined by a linear decision function: Suppose a classification rule satisfies: 1. All points wit…
  11. Q12Consider the following tensor operation in pytorch: What will be the output of the final print statement?
  12. Q13A student is using a single neuron with activation where Can this single neuron represent XOR exactly for the four bina…
  13. Q14Consider the following snippet of a CNN block: A part of which classical CNN architecture is represented by the above c…
  14. Q15In deep CNN architectures like VGGNet, multiple 3×3 convolutional layers are stacked instead of using a single large ke…
  15. Q16A CNN produces an output feature map of size 10x10x64. Global Average Pooling (GAP) is applied to this feature map. Wha…
  16. Q17A feedforward neural network has 2 input neurons, one hidden layer (l = 1) with 2 neurons, and one output neuron (l = 2…
  17. Q18A feedforward neural network has 2 input neurons, one hidden layer (l = 1) with 2 neurons, and one output neuron (l = 2…
  18. Q19Which statement is guaranteed by the Universal Approximation Theorem (UAT)?
  19. Q20A feedforward neural network has 2 input neurons, one hidden layer (l = 1) with 2 neurons, and one output neuron (l = 2…