Quiz Space

Deep Learning · Quiz 1 · 13 Jul 2025 · May 2025 term

Question 9: Consider a neural network for a regression problem with o…

Question 9

+4 marksNumerical answer

Consider a neural network for a regression problem with one input and one output. There is one hidden layer with two sigmoid neurons. The output layer is linear. Ignore biases in all units.

Based on the above data, answer the given subquestions.

Show answer

Correct answer: 1

See the whole paperTake it as a mock test

Question 9 of 14 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 1 paper sat on 13 Jul 2025, in the May 2025 term (IIT M DEGREE AN EXAM QDB2 13 July 2025). It carries 4 marks.

More questions from this paper

  1. Q1Figure question
  2. Q2Which of the following is true?
  3. Q3Figure question
  4. Q4Figure question
  5. Q5To learn the parameters of a neural network for a classification problem, mini-batch gradient descent is run on a datas…
  6. Q6Let h : {0,1}^5 \to {0,1} be a Boolean function. Consider an MP neuron with five binary inputs, all of which are excita…
  7. Q7Let h : {0,1}^5 \to {0,1} be a Boolean function. Consider an MP neuron with five binary inputs, all of which are excita…
  8. Q8Let h : {0,1}^5 \to {0,1} be a Boolean function. Consider an MP neuron with five binary inputs, all of which are excita…
  9. Q10Consider a neural network for a regression problem with one input and one output. There is one hidden layer with two si…
  10. Q11Find the number of weights in the network.
  11. Q12If all the weights in the network have the same value, find the cross entropy loss for an arbitrary data-point. If this…
  12. Q13Starting at (x_0, y_0), run two steps of gradient descent with learning rate \eta = 0.2 to obtain (x_2, y_2). If (x_2, …
  13. Q14Starting at (x_0, y_0), we now turn to momentum based gradient descent. The momentum updates are given below. Starting …