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

DL & GenAI · Quiz 1 · 26 Oct 2025 (Afternoon)

20 questions · 50 marks · 60 min

Answer key Take as mock

Indian Institute of Technology Madras

BS Degree Programme · Examination & Study Paper

Introduction to Deep Learning and Generative AI

Quiz 1 · 26 Oct 2025 (Afternoon)

Official Paper

Examination Instructions & Guidelines

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

Useful Reference Data for this Paper
Note: In all the questions, assume necessary imports wherever applicable.
Q1MCQ2 Marks·Choose one option
Key ↓
1. Atorch.tensor([1, 4, 7])
2. Btorch.tensor([2, 5, 8])
3. Ctorch.tensor([3, 6, 9])
4. Dtorch.tensor([4, 5, 6])
5. Etorch.tensor([5])
Q2MCQ2 Marks·Choose one option
Key ↓
1. A(3, 4) and (3, 4)
2. B(3, 4) and (4, 3)
3. C(4, 3) and (4, 3)
4. D(4, 3) and (3, 4)
Q3MCQ2 Marks·Choose one option
Key ↓
1. A(1, 2, 2)
2. B(2, 2)
3. C(2,)
4. D(1, 1, 2, 2)
5. E(1, 2, 2, 1)
Q4MCQ2 Marks·Choose one option
Key ↓
1. Amodel.cuda()
2. Binput_batch.cuda()
3. Cinput_batch = input_batch.requires_grad_(True)
4. Dinput_batch = input_batch.to(device)
5. Etorch.set_default_tensor_type('torch.cuda.FloatTensor')
Q5MCQ2 Marks·Choose one option
Key ↓
1. AIt prevents parameters from being changed by the optimizer during the forward pass.
2. BIt deallocates the model's parameters from the GPU to save memory.
3. CIt disables the creation of the computational graph, saving memory and speeding up execution.
4. DIt ensures that the model operates entirely on the CPU, preventing unnecessary GPU transfers.
Q6MCQ2 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Q7NAT2 Marks·Write the number
Key ↓
Your answer:
Q8MCQ3 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
5. E
Read the passage below, then answer Q9–Q10
Based on the above data, answer the given subquestions.
Q9MCQ3 Marks·Choose one option
Key ↓
If all the weights are initalized to 0 and the input to the network is also a zero vector, then what should be the value of bias so that the output of the network is 0.5 ?
1. A0.5
2. Bln(5)
3. Cln(1)
4. D1
Q10MCQ4 Marks·Choose one option
Key ↓
1. A
2. B
3. C
4. D
Read the passage below, then answer Q11–Q13
Q11MCQ3 Marks·Choose one option
Key ↓
Select the equation representing the forward pass of the given network:
1. A
2. B
3. C
4. D
Q12NAT6 Marks·Write the number
Key ↓
Your answer:
Q13NAT2 Marks·Write the number
Key ↓
Your answer:
Read the passage below, then answer Q14–Q17
Based on the above data, answer the given subquestions.
Q14NAT3 Marks·Write the number
Key ↓
How many trainable parameters are there in the first convolutional layer including bias (conv1)?
Your answer:
Q15NAT1 Mark·Write the number
Key ↓
What is the total number of trainable parameters in the pooling layers(pool1 and pool2)?
Your answer:
Q16NAT1 Mark·Write the number
Key ↓
How many parameters (weights and biases) does the first fully connected layer (fc1) have?
Your answer:
Q17NAT1 Mark·Write the number
Key ↓
What is the total number of convolution filters used in this CNN?
Your answer:
Read the passage below, then answer Q18–Q20
Based on the above data, answer the given subquestions.
Q18NAT3 Marks·Write the number
Key ↓
Your answer:
Q19NAT3 Marks·Write the number
Key ↓
Your answer:
Q20NAT3 Marks·Write the number
Key ↓
Your answer:

Official Key

Master Answer Key & Explanations

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

Reveal Key

Q1B

Q2B

Q3B

Q4D

Q5C

Q6D

Q759

Q8C

Q9C

Q10D

Q11B

Q121

Q131

Q1480

Q150

Q16100480

Q1724

Q181

Q192

Q20192

Questions and answer keys are reproduced from the official IIT Madras BS papers. BTechi is not affiliated with IIT Madras.