Quiz Space

Deep Learning · End Term · 31 Aug 2025 · May 2025 term · Set QDD3

Question 4: Given the input matrix X and kernel K: X = \begin{bmatrix…

Question 4

+3 marksNumerical answer

Given the input matrix XX and kernel KK:

X=[210101−10321−110−22],K=[010110001]X = \begin{bmatrix} 2 & 1 & 0 & 1 \\ 0 & 1 & -1 & 0 \\ 3 & 2 & 1 & -1 \\ 1 & 0 & -2 & 2 \end{bmatrix}, \quad K = \begin{bmatrix} 0 & 1 & 0 \\ 1 & 1 & 0 \\ 0 & 0 & 1 \end{bmatrix}

  • Perform convolution of KK over XX with stride =1= 1 and no padding to get matrix AA.
  • Apply average pooling on all of AA to produce scalar BB.
  • Apply the ReLU activation on BB to obtain final output y^\hat{y}.

If ∂L∂y^=2\frac{\partial L}{\partial \hat{y}} = 2, compute ∂L∂K11\frac{\partial L}{\partial K_{11}}, where K11K_{11} is the centre element of the kernel. Submit the final answer correct to two decimal places.

Show answer

Correct answer: 1.5 (accepted within ±0.5)

Question 4 of 19 in the IIT Madras BS Deep Learning (Deep Learning) End Term paper sat on 31 Aug 2025, in the May 2025 term (IIT M IMPROVEMENT FN EXAM QIC1 31 Aug 2025). It carries 3 marks.

This question was also asked in

More questions from this paper

  1. Q1Consider the following two statements regarding model performance:\ Statement 1: A model achieving zero training loss i…
  2. Q2How does unsupervised layerwise pretraining help in alleviating the vanishing gradient problem?
  3. Q3A dataset is given by X = \begin{bmatrix} 1 & 2 & 0 & 5 & 0 \ 1 & 0 & 3 & 0 & 0 \ 1 & 1 & 0 & 1 & 1 \ 1 & -1 & 0 & 0 & …
  4. Q5Suppose you are given three encoder hidden states at time t: h_j = h_1 = \begin{bmatrix} 1 \ 0 \end{bmatrix}, \quad h_2…
  5. Q6Suppose you are given three encoder hidden states at time t: h_j = h_1 = \begin{bmatrix} 1 \ 0 \end{bmatrix}, \quad h_2…
  6. Q7Suppose you are given three encoder hidden states at time t: h_j = h_1 = \begin{bmatrix} 1 \ 0 \end{bmatrix}, \quad h_2…
  7. Q8Sequence Length : t Number of Heads : h Embedding dimension : d_{\text{model}} Input X \in \mathbb{R}^{d_{\text{model}}…
  8. Q9Sequence Length : t Number of Heads : h Embedding dimension : d_{\text{model}} Input X \in \mathbb{R}^{d_{\text{model}}…
  9. Q10Sequence Length : t Number of Heads : h Embedding dimension : d_{\text{model}} Input X \in \mathbb{R}^{d_{\text{model}}…
  10. Q11Consider a CBOW model for learning word embeddings. The vocabulary is made up of three words, {good, bad, ugly}. W and …
  11. Q12Consider a CBOW model for learning word embeddings. The vocabulary is made up of three words, {good, bad, ugly}. W and …
  12. Q13Consider a CBOW model for learning word embeddings. The vocabulary is made up of three words, {good, bad, ugly}. W and …
  13. Q14Based on the above data, answer the given subquestions.
  14. Q15Based on the above data, answer the given subquestions.
  15. Q16Based on the above data, answer the given subquestions.
  16. Q17Based on the above data, answer the given subquestions.
  17. Q18Based on the above data, answer the given subquestions.
  18. Q19Based on the above data, answer the given subquestions.