Quiz Space

Deep Learning · Quiz 2 · 23 Nov 2025 · September 2025 term

Question 7: After training a linear regression model on a large train…

Question 7

+3 marksOne or more correct options

After training a linear regression model on a large training set of size
, it achieves a training

error of
. Analysis of the residual plot shows a clear non-linear pattern, suggesting the model is underfitting the data. Which two of the following modifications are most likely to improve the model’s performance by increasing its capacity to capture non-linear relationships?

Select all that apply.

  1. A

    Adding a regularization term (such as L2 or L1 penalty) to the mean squared error loss function.

  2. B

    Using a 2-hidden layer feedforward network with ReLU activation functions in place of linear regression.

  3. C

    Applying a polynomial feature transformation of degree
    to the input variables.

  4. D

    Standardizing all training samples to have mean zero and unit variance.

  5. E

    Using a 5-hidden layer feedforward network without non-linear activation functions in place of linear regression.

Show answer

Correct answers

  • B

    Using a 2-hidden layer feedforward network with ReLU activation functions in place of linear regression.

  • C

    Applying a polynomial feature transformation of degree
    to the input variables.

See the whole paperTake it as a mock test

Question 7 of 15 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 2 paper sat on 23 Nov 2025, in the September 2025 term (IIT M IMPROVEMENT AN EXAM QIA2 23 Nov 2025). It carries 3 marks.

More questions from this paper

  1. Q1Figure question
  2. Q2Consider a neural network as shown in the figure with 2 input neurons, a hidden layer with 2 neurons (ReLU), and 1 outp…
  3. Q3Which of the following statements are true about a Convolutional (CONV) layer?
  4. Q4Which of the following optimizers adapts the learning rate for each parameter during training?
  5. Q5Which of the following techniques can be used to reduce model overfitting?
  6. Q6Why is bias correction needed in the Adam optimizer?
  7. Q8Consider an Inception module in GoogLeNet with an input feature map of size\ . The module has four branches: •\ Branch …
  8. Q9Consider a fully connected neural network as follows: •\ One input neuron\ •\ A single hidden layer with two neurons\ •…
  9. Q10Consider a fully connected neural network as follows: •\ One input neuron\ •\ A single hidden layer with two neurons\ •…
  10. Q11Consider a fully connected neural network as follows: •\ One input neuron\ •\ A single hidden layer with two neurons\ •…
  11. Q12What will be the input to the Pooling Layer.
  12. Q13Find the output after average pooling. Answer correct up to 2 digits after the decimal.
  13. Q14If\ , compute\ and submit the answer correct up to 2 digits after the decimal
  14. Q15If\ , compute\ . where\ is the top left element of the filter. Submit the answer correct up to two digits after the dec…