Quiz Space

Deep Learning · End Term · 10 May 2026 · January 2026 term

Question 16: Compute the total number of elements in the resulting at…

Question 16

+2 marksNumerical answer

•

Compute the total number of elements in the resulting attention output.

Show answer

Correct answer: 512

See the whole paperTake it as a mock test

Question 16 of 20 in the IIT Madras BS Deep Learning (Deep Learning) End Term paper sat on 10 May 2026, in the January 2026 term (Deep Learning 06 May 26). It carries 2 marks.

More questions from this paper

  1. Q1Figure question
  2. Q2Consider a vanilla Recurrent Neural Network (RNN) and an LSTM network with the same input dimension, hidden dimension, …
  3. Q3Figure question
  4. Q4Figure question
  5. Q5Match the attention mechanism in Column I with the correct description in Column II.
  6. Q6Figure question
  7. Q7Figure question
  8. Q8Figure question
  9. Q9Find the total number of parameters in the network.
  10. Q10The loss is defined as . If then compute .
  11. Q11After training a neural network, the training error is observed to be 10%. It gives the test error to be 56%. Which of …
  12. Q12Consider a transformer model using scaled dot-product attention:
  13. Q13Figure question
  14. Q14Figure question
  15. Q15Which of the following problems of the co-occurrence matrix are addressed by applying Singular Value Decomposition (SVD…
  16. Q17•
  17. Q18Assume a Feed-Forward Network (FFN) follows the Multi-Head Attention layer in the encoder. The FFN consists of two line…
  18. Q19Assume that your CBOW model outputs a probability distribution over a vocabulary of 20,000 words for a given context. I…
  19. Q20In the Skip-gram model with a window size of 2 (on each side), how many unique pairs of target and context words will b…