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

DL for CV · Neural networks & training

33 questions · 55 marks · 3 papers

Answer key

Indian Institute of Technology Madras

BS Degree Programme · Examination & Study Paper

Deep Learning for Computer Vision

Neural networks & training

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.

Quiz 1 · 26 Oct 2025 (AN)Quiz 1

Q1MCQ2 Marks·Choose one option
Asked 13 times Key ↓
1. A0.9829, 4.05, 1, 4.0673, 4.05, 4.05
2. B0.8808, 3.50, 1, 3.54, 3.50, 3.50
3. C0.7311, 2.00, 1, 2.13, 2.00, 2.00
4. D0.5000, 0.00, 0, 0.69, 0.00, 0.00
Q2MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A1→ii, 2→i, 3→iii, 4→iv
2. B1→i, 2→ii, 3→iii, 4→iv
3. C1→i, 2→iv, 3→ii, 4→iii
4. D1→iv, 2→ii, 3→i, 4→iii
Q3MCQ2 Marks·Choose one option
Key ↓
Which is True?
1. ANesterov momentum looks ahead and often converges faster than classical momentum.
2. BA large fixed learning rate always speeds convergence.
3. CAdam uses only a first-moment estimate of gradients.
4. DNone of these
Q4MSQ3 Marks·Choose all correct options
Key ↓
Which statements are true? (Select all that apply)
1. A
2. B
3. C
4. D
Q5MSQ3 Marks·Choose all correct options
Key ↓
Which statements are false?
1. AMomentum maintains an EMA-like velocity of gradients/updates.
2. BRMSProp normalizes step sizes by a running RMS of gradients.
3. CIn the Adam optimizer, the hyper-parameters β_1 and β_2 control the exponential decay rates for the moving averages of the gradient and its squared vale. Adam with reduces to SGD with momentum. β_1 = 0 and β_2 = 0 reduces to SGD with momentum.
4. DCosine-annealed warm restarts can help escape sharp minima.
Q6NAT3 Marks·Write the number
Asked 3 times Key ↓
NOTE: Enter your answer in three decimal places.
Your answer:
Q7NAT3 Marks·Write the number
Key ↓
Your answer:
Q8NAT3 Marks·Write the number
Key ↓
Your answer:

End Term · 31 Aug 2025 (FN)End Term

Q9MCQ2 Marks·Choose one option
Asked 2 times Key ↓
1. A1→ vi, 2→ iii, 3 →v, 4 → i
2. B1→ i, 2→ iv, 3 → iii, 4→ ii
3. C1→ i, 2→ v, 3 → iii, 4→ iv
4. D1→ iv, 2→ iii, 3→ ii, 4 → i
Q10MCQ2 Marks·Choose one option
Asked 2 times Key ↓
Which one of the following statements regarding hyperparameter tuning is false?
1. AValidation set is the best choice for tuning hyperparameters
2. BPicking hyperparameters that perform the best on the training set leads to overfitting
3. CTuning hyperparameters on the test set is an acceptable approach to find the most powerful model for generalization performance
4. DTest set performance, with hyperparameters tuned on the validation set, would be a realistic measure of how the model will generalize to new data.
Q11MSQ2 Marks·Choose all correct options
Asked 2 times Key ↓
Which one of the following statements is true:
1. AWeight change criterion is a method of ‘early stopping’ that checks whether or not the error is dropping over epochs to decide whether to continue training or stop.
2. BL1 norm tends to create more sparse weights than L2 norm.
3. CDuring the training phase, for each iteration, Dropout ignores a random fraction, p, of nodes, and accounts for it in the test phase by scaling down the activations by a factor of p.
4. DA single McCulloch-Pitts neuron is capable of modeling AND, OR, XOR, NOR, and NAND functions.
Q12MSQ2 Marks·Choose all correct options
Key ↓
Which of the following statements are true? (Select all that apply)
1. A
2. B
3. C
4. D
Q13NAT2 Marks·Write the number
Asked 3 times Key ↓
Your answer:
Read the passage below, then answer Q14–Q15
Q14NAT1 Mark·Write the number
Asked 4 times Key ↓
Your answer:
Q15NAT1 Mark·Write the number
Asked 4 times Key ↓
Your answer:
Read the passage below, then answer Q16–Q21
Based on the above data, answer the given subquestions.
Q16NAT1 Mark·Write the number
Asked 13 times Key ↓
Sigmoid _______________
Your answer:
Q17NAT1 Mark·Write the number
Asked 13 times Key ↓
Linear _______________
Your answer:
Q18NAT1 Mark·Write the number
Asked 13 times Key ↓
Indicator Function _______________
Your answer:
Q19NAT1 Mark·Write the number
Asked 13 times Key ↓
Softplus _______________
Your answer:
Q20NAT1 Mark·Write the number
Asked 13 times Key ↓
ReLu _______________
Your answer:
Q21NAT1 Mark·Write the number
Asked 13 times Key ↓
Leaky-ReLu _______________
Your answer:

End Term · 31 Aug 2025 (AN)End Term

Q22MCQ2 Marks·Choose one option
Key ↓
Consider the following Pytorch code: 1. x = torch.tensor([[-3.,2.,3.],[4.,-5.,7.],[20.,3.,2.]]) 2. print(torch.mean(x,dim=0,keepdim=True)) The output of the code is:
1. Atensor([ 7., 0., 4.])
2. Btensor([[ -7., 10., -4.]])
3. Ctensor([[ -7.],[7.],[4.]])
4. Dtensor([ -7., 7., 3.])
5. Etensor([[7., 0., 4.]])
6. Ftensor([[ 0.],[7.],[4.]])
Q23MCQ2 Marks·Choose one option
Asked 2 times Key ↓
Which one of the following statements regarding hyperparameter tuning is false?
1. AValidation set is the best choice for tuning hyperparameters
2. BPicking hyperparameters that perform the best on the training set leads to overfitting
3. CTuning hyperparameters on the test set is an acceptable approach to find the most powerful model for generalization performance
4. DTest set performance, with hyperparameters tuned on the validation set, would be a realistic measure of how the model will generalize to new data.
Q24MSQ2 Marks·Choose all correct options
Asked 2 times Key ↓
Which one of the following statements is true:
1. AWeight change criterion is a method of ‘early stopping’ that checks whether or not the error is dropping over epochs to decide whether to continue training or stop.
2. BL1 norm tends to create more sparse weights than L2 norm.
3. CDuring the training phase, for each iteration, Dropout ignores a random fraction, p, of nodes, and accounts for it in the test phase by scaling down the activations by a factor of p.
4. DA single McCulloch-Pitts neuron is capable of modeling AND, OR, XOR, NOR, and NAND functions.
Q25NAT2 Marks·Write the number
Asked 3 times Key ↓
Your answer:
Read the passage below, then answer Q26–Q27
Based on the above data, answer the given subquestions.
Q26NAT1 Mark·Write the number
Asked 4 times Key ↓
Your answer:
Q27NAT1 Mark·Write the number
Asked 4 times Key ↓
Your answer:
Read the passage below, then answer Q28–Q33
Based on the above data, answer the given subquestions.
Q28NAT1 Mark·Write the number
Asked 13 times Key ↓
Sigmoid ______________
Your answer:
Q29NAT1 Mark·Write the number
Asked 13 times Key ↓
Linear ______________
Your answer:
Q30NAT1 Mark·Write the number
Asked 13 times Key ↓
Indicator Function ______________
Your answer:
Q31NAT1 Mark·Write the number
Asked 13 times Key ↓
Softplus _____________
Your answer:
Q32NAT1 Mark·Write the number
Asked 13 times Key ↓
ReLU _______________
Your answer:
Q33NAT1 Mark·Write the number
Asked 13 times Key ↓
Leaky-ReLU _____________
Your answer:

Official Key

Master Answer Key & Explanations

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

Reveal Key

Q1A

Q2B

Q3A

Q4B, C, D

Q5C

Q61.223

Q70

Q899

Q9D

Q10C

Q11B, C

Q12B, C

Q13-0.215 to -0.205

Q14-2

Q155

Q160.95

Q173

Q181

Q193.05

Q203

Q213

Q22E

Q23C

Q24B, C

Q250.93 to 0.94

Q26-2

Q275

Q280.99

Q2926.01

Q301

Q3126.01

Q3226.01

Q3326.01

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.