Quiz Space

Deep Learning · Quiz 2 · 24 Mar 2024 · January 2024 term

Question 3: Suppose you have a deep neural network trained on a datas…

Question 3

+3 marksOne correct option

Suppose you have a deep neural network trained on a dataset with a small amount of labeled examples. After applying L2 regularization during training with a fixed value of regularization parameter, the following observations are made:
• The empirical error decreases significantly.
• The true error remains high.
• The variance of the error on different subsets of the training data is relatively low.
• When tested on a diverse set of unseen data, the model’s performance is inconsistent. Which of the following statements provides a plausible explanation for this scenario?

  1. A

    The model is underfitting due to excessive regularization.

  2. B

    L2 regularization effectively reduces both overfitting and underfitting.

  3. C

    The inconsistency in performance on unseen data is expected due to the limited labeled examples in the training set.

  4. D

    The model is still overfitting to the training data, and the regularization parameter needs adjustment.

Show answer

Correct answer

  • D

    The model is still overfitting to the training data, and the regularization parameter needs adjustment.

Question 3 of 16 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 2 paper sat on 24 Mar 2024, in the January 2024 term (IIT M DEGREE AN EXAM QDB2 24 Mar 2024). It carries 3 marks.

More questions from this paper

  1. Q1What are the possible outcomes if we don’t do bias correction in ADAM?
  2. Q2Consider the assertion and the corresponding reason,\ Assertion (A): The RMSProp Algorithm starts oscillating around th…
  3. Q4What are the maximum and minimum possible values of the derivative of sigmoid function?
  4. Q5Consider a feed-forward neural network containing three inputs and one output. It contains 50 hidden layers, each conta…
  5. Q6Suppose we have a neural network with two hidden layers, each containing two neurons. The network contains two inputs a…
  6. Q7Consider a neural network with one hidden layer containing two neurons. The input layer contains 2 neurons and the outp…
  7. Q8Which of the following statements are true w.r.t. AdaDelta Algorithm?
  8. Q9After training a neural network using vanilla gradient descent, you notice that it performs exceptionally well on the t…
  9. Q10Which of the following optimization algorithms encounter problem of oscillating around the minima?
  10. Q11Consider a network where sigmoid activation is used at all hidden layers. Which of the following will be true?
  11. Q12Consider an Input matrix X of shape 4×4 and the kernel (filter) of shape 3×3 with a bias b = 1. Assume, stride equals 1…
  12. Q13Consider an Input matrix X of shape 4×4 and the kernel (filter) of shape 3×3 with a bias b = 1. Assume, stride equals 1…
  13. Q14Consider an Input matrix X of shape 4×4 and the kernel (filter) of shape 3×3 with a bias b = 1. Assume, stride equals 1…
  14. Q15What is the value of stride s?. Assume zero padding (p = 0)
  15. Q16How many parameters (excluding bias) are there in the convolutional layer?