Quiz Space

Deep Learning · Quiz 1 · 19 Jul 2026 · May 2026 term

Question 10: Which of the following statements regarding perceptrons …

Question 10

+4 marksOne or more correct options

Which of the following statements regarding perceptrons and sigmoid neurons are correct?

Select all that apply.

  1. A

    The output of a perceptron changes abruptly when the weighted sum of inputs crosses the threshold, whereas the output of a sigmoid neuron changes smoothly.

  2. B

    The sigmoid activation function is differentiable, making it suitable for gradient-based learning algorithms.

  3. C

    By choosing sufficiently large weights, the output of a sigmoid neuron can closely approximate the output of a perceptron.

  4. D

    A multilayer network of perceptrons with a single hidden layer can represent any Boolean function exactly.

  5. E

    A multilayer network of sigmoid neurons with a single hidden layer can approximate any continuous function to any desired precision, provided enough hidden neurons are available.

  6. F

    A single sigmoid neuron can represent every non-linear decision boundary in .

Show answer

Correct answers

  • A

    The output of a perceptron changes abruptly when the weighted sum of inputs crosses the threshold, whereas the output of a sigmoid neuron changes smoothly.

  • B

    The sigmoid activation function is differentiable, making it suitable for gradient-based learning algorithms.

  • C

    By choosing sufficiently large weights, the output of a sigmoid neuron can closely approximate the output of a perceptron.

  • D

    A multilayer network of perceptrons with a single hidden layer can represent any Boolean function exactly.

  • E

    A multilayer network of sigmoid neurons with a single hidden layer can approximate any continuous function to any desired precision, provided enough hidden neurons are available.

See the whole paperTake it as a mock test

Question 10 of 20 in the IIT Madras BS Deep Learning (Deep Learning) Quiz 1 paper sat on 19 Jul 2026, in the May 2026 term (Deep Learning 16 Jul 26). It carries 4 marks.

More questions from this paper

  1. Q1State whether the following statement is true or false. The decision boundary learned by a neural network is always non…
  2. Q2Consider the following two statements and select the correct options. Statement I: A single MP neuron can be used to re…
  3. Q3Two runs of gradient descent on from the same starting point produce Graph X and Graph Y using two learning rates: Whic…
  4. Q4The loss function is minimized starting at with using four methods: Vanilla Gradient Descent ( ), and momentum based gr…
  5. Q5A perceptron is being trained on a 2D dataset using the Perceptron Learning Algorithm. The current weight vector For a …
  6. Q6Which of the following statements are TRUE about training neural networks?
  7. Q7Consider a hidden layer with neurons, all initialized with identical weight vectors and identical bias . The activation…
  8. Q8Consider an MP neuron with three inputs Inputs and are excitatory, while is inhibitory. The threshold of the neuron is …
  9. Q9Consider a perceptron with initial parameters The perceptron predicts class if and class otherwise. Whenever a training…
  10. Q11Which of the following statements are true regarding the sigmoid function and its Taylor series approximation? Let be t…
  11. Q12Consider a regression problem of predicting the price of a house using two features: Overall quality , living area (sq.…
  12. Q13Consider a 3-class softmax output with pre-activations . Find the value of for which the predicted probability of class…
  13. Q14Consider a sigmoid neuron For a training example , let The squared-error loss is given by Find the value of . Round you…
  14. Q15You build a feedforward neural network to predict which of 10 categories a product belongs to, based on 50 numerical fe…
  15. Q16You build a feedforward neural network to predict which of 10 categories a product belongs to, based on 50 numerical fe…
  16. Q17With vanilla gradient descent, how many parameter updates does the network perform per epoch?
  17. Q18You switch to mini-batch gradient descent with batch size . How many parameter updates does the network now perform per…
  18. Q19You build a feedforward neural network to predict which of 10 categories a product belongs to, based on 50 numerical fe…
  19. Q20You are training a neural network to classify 200 species of birds from audio recordings. You have collected a dataset …