BTechibtechi.in
Loading Loading
Free IIT Madras BS notes, PYQs and mock tests at btechi.in

DL for CV · RNNs, attention & transformers

42 questions · 44.99999999999999 marks · 3 papers

Answer key

Indian Institute of Technology Madras

BS Degree Programme · Examination & Study Paper

Deep Learning for Computer Vision

RNNs, attention & transformers

Official Paper

Examination Instructions & Guidelines

Solve on notebook/paper first before checking solutions.
MCQ: Exactly 1 option is correct. Negative marking applies.
MSQ: One or more options correct. Select all to score.
NAT: Numerical response. No negative marking.
Scientific calculator allowed for all calculations.
Official answer key is sealed at the end of this sheet.

End Term · 31 Aug 2025 (FN)End Term

Q1MCQ2 Marks·Choose one option
Key ↓
1. ASigmoid of alignment scores
2. BReLU of alignment scores
3. CSoftmax of alignment scores
4. DLinear projections of alignment scores
Q2MCQ2 Marks·Choose one option
Asked 4 times Key ↓
Which one of the following statements is true?
1. AAttention mechanisms cannot be applied to the bidirectional RNN model
2. BAn image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network
3. COne of the key components in the vanilla transformer are the recurrent connections that help them to deal with variable input length.
4. DNone of these
Q3MSQ2 Marks·Choose all correct options
Asked 3 times Key ↓
Which of the following techniques help control the exploding or vanishing gradient problem in recurrent neural networks?
1. AGradient clipping
2. BUse ReLU activation funtion to control exploding gradient and sigmoid activation to control vanishing gradients
3. CUse Long Short-Term Memory (LSTM)
4. DUse data augmentation methods (for example, reversing the input sequence)

End Term · 31 Aug 2025 (AN)End Term

Q4MCQ2 Marks·Choose one option
Key ↓
What is the correct order of operations for processing an image through a Vision Transformer (ViT)?
1. AImage patching → Positional embedding → Linear projection of flattened patches → Transformer encoder→ Classification head
2. BImage patching → Linear projection of flattened patches → Positional embedding → Transformer encoder→ Classification head
3. CPositional embedding → Image patching → Linear projection of flattened patches → Transformer encoder→ Classification head
4. DLinear projection of Images → Image patching → Positional embedding → Transformer encoder → Classification head
5. ELinear projection of Images → Image patching → Positional embedding → Transformer encoder → Transformer decoder→ Classification head
Q5MCQ2 Marks·Choose one option
Asked 4 times Key ↓
Which one of the following statements is false? (Pick the most appropriate one.)
1. AAttention mechanisms can be applied to the bidirectional RNN model
2. BAn image captioning network can be trained end-to-end even though we are using 2 different modalities to train the network
3. COne of the key components in the vanilla transformer is the recurrent connection that help them to deal with variable input length.
4. DAll of these.
Q6MCQ2 Marks·Choose one option
Asked 2 times Key ↓
In which one of the following applications would you use a many- to-one RNN architecture? Choose the most appropriate answer.
1. AInput is a review of a movie and output is the sentiment of the given review
2. BInput is an image and output is the textual description of the given image
3. CInput is an image and output is the class to which the given image belongs
4. DInput is a sentence in English language and output is the same sentence translated to Hindi language

Quiz 2 · 3 Aug 2025 (AN)Quiz 2

Q7MCQ2 Marks·Choose one option
Asked 4 times Key ↓
Which one of the following statements is True?
1. AAttention mechanisms can be applied to the bidirectional RNN model
2. BAn image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network
3. COne of the key components in the vanilla transformer are the recurrent connections that help them to deal with variable input length.
4. DAll of these.
Q8MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A
2. B
3. C
4. D
Q9MCQ2 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Q10MCQ2 Marks·Choose one option
Asked 3 times Key ↓
Which of the following techniques help mitigate the vanishing gradient problem in recurrent neural networks? 1. Gradient clipping 2. Use of ReLU activation to preserve gradient flow 3. Use of LSTM units 4. Data augmentation (e.g., reversing input sequence)
1. A1 and 2 only
2. B2 and 3 only
3. C3 and 4 only
4. D1, 2, and 3 only
Q11MCQ2 Marks·Choose one option
Asked 3 times Key ↓
Which of the following techniques help mitigate the exploding gradient problem in recurrent neural networks? 1. Gradient clipping 2. Use of Sigmoid activation to prevent gradient growth 3. Use of LSTM units 4. Data augmentation (e.g., reversing input sequence)
1. A1 and 2 only
2. B1 and 3 only
3. C1, 2, and 3
4. DAll of these
Q12MCQ2 Marks·Choose one option
Asked 4 times Key ↓
Which one of the following statements is false? (Pick the most appropriate one.)
1. AAttention mechanisms cannot be applied to the bidirectional RNN model
2. BAn image captioning network cannot be trained end-to-end even though we are using 2 different modalities to train the network
3. COne of the key components in the vanilla transformer is the recurrent connection that help them to deal with variable input length.
4. DAll of these
Q13MSQ3 Marks·Choose all correct options
Key ↓
Which of the following is true regarding Hard Attention and Soft Attention?
1. ASoft Attention is smooth and differentiable
2. BVariance reduction techniques are used to train Soft Attention models
3. CSoft Attention is computationally cheaper than Hard Attention when the source input is large
4. DThe inference (test time) overhead is low in Hard Attention when compared to Soft Attention models
Read the passage below, then answer Q14–Q15
Suppose you want to build an encoder-decoder recurrent model with attention. The context vector at time step t is given by:
where α_(tj) refers to the alignment score between the decoder state at time t _____________and the encoder state at time _____________. Note: Please write your answer using variables
Based on the above data, answer the given subquestions.
Q14NAT1 Mark·Write the number
Key ↓
Decoder state at time t : _______________
Your answer:
Q15Short answer1 Mark·Write the answer
Key ↓
Encoder state at time: _______________
Your answer:
Read the passage below, then answer Q16–Q21
Consider a Gated Recurrent Unit (GRU) cell at time step ’t’.
For each of the entities in the given subquestions, enter the appropriate number from the figure that corresponds to it:
Based on the above data, answer the given subquestions.
Q16NAT0.66 Marks·Write the number
Key ↓
Hidden state h_(t−1)______________
Your answer:
Q17NAT0.66 Marks·Write the number
Key ↓
Hidden state h_t_____________
Your answer:
Q18NAT0.67 Marks·Write the number
Key ↓
Current Input x_t________________
Your answer:
Q19NAT0.67 Marks·Write the number
Key ↓
Update gate z_t_______________
Your answer:
Q20NAT0.67 Marks·Write the number
Key ↓
Reset gate r_t ______________
Your answer:
Q21NAT0.67 Marks·Write the number
Key ↓
New hidden state content e_h____________
Your answer:
Read the passage below, then answer Q22–Q26
Based on the above data, answer the given subquestions.
Q22NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix U1 is:______________
Your answer:
Q23NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix V1 is:______________
Your answer:
Q24NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix U2 is:__________________
Your answer:
Q25NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix V2 is:___________________
Your answer:
Q26NAT0.8 Marks·Write the number
Key ↓
Number of weights in Weight Matrix W is:_______________
Your answer:
Read the passage below, then answer Q27–Q34
Q27NAT0.5 Marks·Write the number
Key ↓
e_(21): _________________
Your answer:
Q28NAT0.5 Marks·Write the number
Key ↓
e_(22): _________________
Your answer:
Q29NAT0.5 Marks·Write the number
Key ↓
e_(23): _________________
Your answer:
Q30NAT0.5 Marks·Write the number
Key ↓
α_(21): _________________
Your answer:
Q31NAT0.5 Marks·Write the number
Key ↓
α_(22): _________________
Your answer:
Q32NAT0.5 Marks·Write the number
Key ↓
α_(23): _________________
Your answer:
Q33NAT0.5 Marks·Write the number
Key ↓
c_(21): _________________
Your answer:
Q34NAT0.5 Marks·Write the number
Key ↓
c_(22): _________________
Your answer:
Read the passage below, then answer Q35–Q42
Q35NAT0.5 Marks·Write the number
Key ↓
e_(21):_________________
Your answer:
Q36NAT0.5 Marks·Write the number
Key ↓
e_(22):_________________
Your answer:
Q37NAT0.5 Marks·Write the number
Key ↓
e_(23):_________________
Your answer:
Q38NAT0.5 Marks·Write the number
Key ↓
α_(21):_________________
Your answer:
Q39NAT0.5 Marks·Write the number
Key ↓
α_(22):_________________
Your answer:
Q40NAT0.5 Marks·Write the number
Key ↓
α_(23):_________________
Your answer:
Q41NAT0.5 Marks·Write the number
Key ↓
c_(21):_________________
Your answer:
Q42NAT0.5 Marks·Write the number
Key ↓
c_(22):_________________
Your answer:

Official Key

Master Answer Key & Explanations

Official answer keys from IIT Madras BS past papers. Click any question to review.

Reveal Key

Q1C

Q2D

Q3A, C, D

Q4B

Q5C

Q6A

Q7A

Q8B

Q9D

Q10B

Q11B

Q12D

Q13A, C, D

Q14-1

Q15j

Q164

Q176

Q183

Q191

Q202

Q215

Q2250

Q2325

Q24100

Q25400

Q26800

Q271

Q280

Q292

Q300.24 to 0.25

Q310.09 to 0.1

Q320.66 to 0.68

Q331.5 to 1.6

Q342.5 to 2.6

Q35-0.01 to 0.01

Q36-0.462

Q370.462

Q380.32 to 0.34

Q390.22 to 0.24

Q400.43 to 0.45

Q411.4 to 1.6

Q422.4 to 2.6

Detailed Answer Notes & Working

Q15Answer: j: Case-sensitive: the answer must match exactly.

Questions and answer keys are reproduced from the official IIT Madras BS papers. Topics and repeated question types are BTechi’s own grouping. BTechi is not affiliated with IIT Madras.