da2001_2025T3_Q1_AN.pdf
Introduction to Deep Learning and Generative AI(DL GENAI) · Quiz 1 · Sep 2025
← Course papers · Start practice / exam
Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.
Question 237 MCQ · 0.0 marks
**Note:** In all the questions, assume necessary imports wherever applicable.
Instructions has been mentioned above.
This Instructions is just for a reference & not for an evaluation.
A published solution is not available for this question yet.
Question 238 MCQ · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_2_0]]

torch.tensor([1, 4, 7])
torch.tensor([2, 5, 8])
torch.tensor([3, 6, 9])
torch.tensor([4, 5, 6])
torch.tensor([5])
A published solution is not available for this question yet.
Question 239 MCQ · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_2_1]]

(3, 4) and (3, 4)
(3, 4) and (4, 3)
(4, 3) and (4, 3)
(4, 3) and (3, 4)
A published solution is not available for this question yet.
Question 240 MCQ · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_3_2]]

(1, 2, 2)
(2, 2)
(2,)
(1, 1, 2, 2)
(1, 2, 2, 1)
A published solution is not available for this question yet.
Question 241 MCQ · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_4_3]]

model.cuda()
input_batch.cuda()
input_batch = input_batch.requires_grad_(True)
input_batch = input_batch.to(device)
torch.set_default_tensor_type('torch.cuda.FloatTensor')
A published solution is not available for this question yet.
Question 242 MCQ · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_5_4]]

It prevents parameters from being changed by the optimizer during the
forward pass.
It deallocates the model's parameters from the GPU to save memory.
It disables the creation of the computational graph, saving memory and
speeding up execution.
It ensures that the model operates entirely on the CPU, preventing
unnecessary GPU transfers.
A published solution is not available for this question yet.
Question 243 MCQ · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_5_5]]

[[IMAGE:2dbe5408150fb0b2_5_6]]

[[IMAGE:2dbe5408150fb0b2_5_7]]

[[IMAGE:2dbe5408150fb0b2_5_8]]

[[IMAGE:2dbe5408150fb0b2_5_9]]

A published solution is not available for this question yet.
Question 244 NAT · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_6_10]]

A published solution is not available for this question yet.
Question 245 MCQ · 3.0 marks
[[IMAGE:2dbe5408150fb0b2_7_11]]

[[IMAGE:2dbe5408150fb0b2_7_12]]

[[IMAGE:2dbe5408150fb0b2_7_13]]

[[IMAGE:2dbe5408150fb0b2_7_14]]

[[IMAGE:2dbe5408150fb0b2_7_15]]

[[IMAGE:2dbe5408150fb0b2_7_16]]

A published solution is not available for this question yet.
Question 246 MCQ · 3.0 marks
[[IMAGE:2dbe5408150fb0b2_8_17]]
Based on the above data, answer the given subquestions.
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 ?

0.5
ln(5)
ln(1)
1
A published solution is not available for this question yet.
Question 247 MCQ · 4.0 marks
[[IMAGE:2dbe5408150fb0b2_8_17]]
Based on the above data, answer the given subquestions.
[[IMAGE:2dbe5408150fb0b2_8_18]]


[[IMAGE:2dbe5408150fb0b2_9_19]]

[[IMAGE:2dbe5408150fb0b2_9_20]]

[[IMAGE:2dbe5408150fb0b2_9_21]]

[[IMAGE:2dbe5408150fb0b2_9_22]]

A published solution is not available for this question yet.
Question 248 MCQ · 3.0 marks
[[IMAGE:2dbe5408150fb0b2_9_23]]
Select the equation representing the forward pass of the given network:

[[IMAGE:2dbe5408150fb0b2_10_24]]

[[IMAGE:2dbe5408150fb0b2_10_25]]

[[IMAGE:2dbe5408150fb0b2_10_26]]

[[IMAGE:2dbe5408150fb0b2_10_27]]

A published solution is not available for this question yet.
Question 249 NAT · 6.0 marks
[[IMAGE:2dbe5408150fb0b2_9_23]]
[[IMAGE:2dbe5408150fb0b2_10_28]]


A published solution is not available for this question yet.
Question 250 NAT · 2.0 marks
[[IMAGE:2dbe5408150fb0b2_9_23]]
[[IMAGE:2dbe5408150fb0b2_10_29]]


A published solution is not available for this question yet.
Question 251 NAT · 3.0 marks
[[IMAGE:2dbe5408150fb0b2_12_30]]
Based on the above data, answer the given subquestions.
How many trainable parameters are there in the first convolutional layer including bias (conv1)?

A published solution is not available for this question yet.
Question 252 NAT · 1.0 marks
[[IMAGE:2dbe5408150fb0b2_12_30]]
Based on the above data, answer the given subquestions.
What is the total number of trainable parameters in the pooling layers(pool1 and pool2)?

A published solution is not available for this question yet.
Question 253 NAT · 1.0 marks
[[IMAGE:2dbe5408150fb0b2_12_30]]
Based on the above data, answer the given subquestions.
How many parameters (weights and biases) does the first fully connected layer (fc1) have?

A published solution is not available for this question yet.
Question 254 NAT · 1.0 marks
[[IMAGE:2dbe5408150fb0b2_12_30]]
Based on the above data, answer the given subquestions.
What is the total number of convolution filters used in this CNN?

A published solution is not available for this question yet.
Question 255 NAT · 3.0 marks
[[IMAGE:2dbe5408150fb0b2_15_31]]
Based on the above data, answer the given subquestions.
[[IMAGE:2dbe5408150fb0b2_16_32]]


A published solution is not available for this question yet.
Question 256 NAT · 3.0 marks
[[IMAGE:2dbe5408150fb0b2_15_31]]
Based on the above data, answer the given subquestions.
[[IMAGE:2dbe5408150fb0b2_16_33]]


A published solution is not available for this question yet.
Question 257 NAT · 3.0 marks
[[IMAGE:2dbe5408150fb0b2_15_31]]
Based on the above data, answer the given subquestions.
[[IMAGE:2dbe5408150fb0b2_16_34]]


A published solution is not available for this question yet.