MauryaHub PYQ Practice

da2001_2026T1_Q1_NA.pdf

Introduction to Deep Learning and Generative AI(DL GENAI) · Quiz 1 · Jan 2026

← 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 2 MCQ · 2.0 marks

What will be the output of the following PyTorch code? [[IMAGE:6f4499f0a9668d18_3_2]]
Source diagram or notation
  1. 29
  2. 43
  3. 48
  4. 53

A published solution is not available for this question yet.

Question 3 MCQ · 2.0 marks

Consider the following code snippet: [[IMAGE:6f4499f0a9668d18_4_3]] What will be printed?
Source diagram or notation
  1. torch.Size([5, 1, 3, 1]), torch.Size([5, 3,1])
  2. torch.Size([1, 5, 1, 3, 1]), torch.Size([5, 3,1])
  3. torch.Size([5, 1, 3, 1]), torch.Size([5, 3])
  4. torch.Size([5, 3]), torch.Size([5, 3])

A published solution is not available for this question yet.

Question 4 MCQ · 2.0 marks

You want to train a linear model using stochastic gradient descent (SGD). Assume that the loss function and training loop are implemented correctly. Which of the following model definitions will result in the weights being updated during training?
  1. [[IMAGE:6f4499f0a9668d18_4_4]]
    Source diagram or notation
  2. [[IMAGE:6f4499f0a9668d18_4_5]]
    Source diagram or notation
  3. [[IMAGE:6f4499f0a9668d18_5_6]]
    Source diagram or notation

A published solution is not available for this question yet.

Question 5 MCQ · 2.0 marks

Consider the following training loop: [[IMAGE:6f4499f0a9668d18_5_7]] Which statement best describes the problem in this training loop?
Source diagram or notation
  1. The forward pass is missing
  2. Gradients accumulate across epochs, leading to incorrect updates
  3. The optimizer cannot update parameters without model.eval()
  4. The loss function cannot compute gradients

A published solution is not available for this question yet.

Question 6 MCQ · 2.0 marks

You are given a dataset of 10 × 10 grayscale images. Your goal is to build a 5-class classifier. You have to adopt one of the following two
  1. p_A > p_B
  2. p_A = p_B
  3. p_A < p_B

A published solution is not available for this question yet.

Question 7 MCQ · 2.0 marks

An image contains 16 channels. Which of the following code snippets correctly creates a convolution layer for this image?
  1. [[IMAGE:6f4499f0a9668d18_6_10]]
    Source diagram or notation
  2. [[IMAGE:6f4499f0a9668d18_6_11]]
    Source diagram or notation
  3. [[IMAGE:6f4499f0a9668d18_6_12]]
    Source diagram or notation
  4. [[IMAGE:6f4499f0a9668d18_6_13]]
    Source diagram or notation

A published solution is not available for this question yet.

Question 8 MCQ · 2.0 marks

Consider the following pytorch code to preprocess the FashionMNIST dataset. [[IMAGE:6f4499f0a9668d18_6_14]] Which of the following hold true?
Source diagram or notation
  1. The images in train_dataset will be converted to tensors and normalized before being returned.
  2. The dataset will return normalized images in the range [−1,1] because FashionMNIST is grayscale.
  3. The transforms are automatically applied to the test split while they are not applied to train split.
  4. The dataset will return PIL images and not tensors.

A published solution is not available for this question yet.

Question 9 MCQ · 2.0 marks

An input volume has shape 6x6x2 (height=6, width=6, depth=2 channels). Perform the following two steps on it. ● Step 1: Apply 2x2 Max Pooling with stride=2 ● Step 2: Then, apply 1x1 Convolution with 4 filters. What is the shape of the final output volume?
  1. 3x3x2
  2. 3x3x4
  3. 6x6x4
  4. 3x3x8

A published solution is not available for this question yet.

Question 10 MCQ · 2.0 marks

In an Inception module, four parallel paths produce outputs of shapes: 28x28x64, 28x28x128, 28x28x32, and 28x28x32. After concatenation, what is the output shape?
  1. 112×28×128
  2. 28×112×256
  3. 28×28×256
  4. 112×112×256

A published solution is not available for this question yet.

Question 11 MCQ · 2.0 marks

A CNN produces an output feature map of size 7x7x512, which is followed by Global Average Pooling (GAP) and then a fully connected layer with 10 output classes. Which of the following statements is correct?
  1. GAP converts the feature map into a 49 × 512 vector before classification
  2. GAP produces a 512-dimensional vector, resulting in 5120 trainable parameters in the final layer
  3. GAP produces a 7 × 7 × 1 feature map, followed by a 10-unit fully connected layer
  4. GAP increases the number of parameters compared to flattening

A published solution is not available for this question yet.

Question 12 MCQ · 3.0 marks

Consider the following code snippet: [[IMAGE:6f4499f0a9668d18_8_15]] What will be printed?
Source diagram or notation
  1. torch.Size([3, 3, 4]), torch.Size([3, 3, 4]), 72
  2. torch.Size([3, 3, 4]), torch.Size([3, 4]), 72
  3. torch.Size([9, 4]), torch.Size([9, 4]), 72
  4. torch.Size([3, 3, 4]), torch.Size([3, 3, 4]), 36

A published solution is not available for this question yet.

Question 13 MCQ · 3.0 marks

A CNN uses three consecutive 3x3 convolution layers with stride 1 and no pooling. What is the receptive field of a neuron in the third layer?
  1. 3x3
  2. 5x5
  3. 7x7
  4. 9x9

A published solution is not available for this question yet.

Question 14 MCQ · 3.0 marks

An input feature map of size 32x32 is convolved using SAME padding in the following two independent cases: Case I: ● Filter size: 5x5 ● Stride: 1 Case II: ● Filter size: 3x3 ● Stride: 1 What amount of padding is applied on each side (top, bottom, left, right) in Case I and Case II, respectively?
  1. Case I: 2 pixels, Case II: 1 pixel
  2. Case I: 1 pixel, Case II: 2 pixels
  3. Case I: 2 pixels, Case II: 0 pixels
  4. Case I: 4 pixels, Case II: 2 pixels

A published solution is not available for this question yet.

Question 15 NAT · 2.0 marks

Consider an input image of size 12x12x4. In the convolution layer a single filter of size 12 x 12 is passed to the image. Now consider the image is resized to 14x14x4. How many additional parameters will be added to the convolution layer?

    A published solution is not available for this question yet.

    Question 16 MSQ · 3.0 marks

    A hidden layer in the feed_forward network of a CNN contains 5 neurons labelled A,B,C,D,E. We apply dropout to this hidden layer to prevent overfitting. During training the following observations occured - Epoch 1 - B and E were dropped out Epoch 2 - A and D were dropped out Select the false statements :
    1. During epoch 3 of training C will be dropped out
    2. During epoch 4 of training none of the neurons will be dropped out for sure since all of them have been dropped in one of the previous epochs.
    3. During inference all of A,B,C,D and E have equal chances of being dropped out
    4. During inference none of the neurons will be dropped out.

    A published solution is not available for this question yet.

    Question 17 NAT · 3.0 marks

    Consider the following CNN : [[IMAGE:6f4499f0a9668d18_11_16]] Calculate the total number of parameters in the CNN.
    Source diagram or notation

      A published solution is not available for this question yet.

      Question 18 MCQ · 2.0 marks

      Consider the below neural network with **fixed weights** and answer the given subquestions: [[IMAGE:6f4499f0a9668d18_12_17]]
      Given the input [[IMAGE:6f4499f0a9668d18_12_18]] , what is the output [[IMAGE:6f4499f0a9668d18_12_19]] of the network?
      Source diagram or notationSource diagram or notationSource diagram or notation
      1. 0
      2. 1
      3. 2
      4. 2.5

      A published solution is not available for this question yet.

      Question 19 NAT · 2.0 marks

      Consider the below neural network with **fixed weights** and answer the given subquestions: [[IMAGE:6f4499f0a9668d18_12_17]]
      Assume the **target value** is [[IMAGE:6f4499f0a9668d18_12_20]] . Using **Mean Squared Error (MSE)** as the loss function, compute the numerical value of the loss assuming the input [[IMAGE:6f4499f0a9668d18_12_21]] .
      Source diagram or notationSource diagram or notationSource diagram or notation

        A published solution is not available for this question yet.

        Question 20 MCQ · 3.0 marks

        Consider the below neural network with **fixed weights** and answer the given subquestions: [[IMAGE:6f4499f0a9668d18_12_17]]
        For which of the following conditions on [[IMAGE:6f4499f0a9668d18_13_22]] will the first neuron of the hidden layer [[IMAGE:6f4499f0a9668d18_13_23]] not be activated ( [[IMAGE:6f4499f0a9668d18_13_24]] )?
        Source diagram or notationSource diagram or notationSource diagram or notationSource diagram or notation
        1. [[IMAGE:6f4499f0a9668d18_13_25]]
          Source diagram or notation
        2. [[IMAGE:6f4499f0a9668d18_13_26]]
          Source diagram or notation
        3. [[IMAGE:6f4499f0a9668d18_13_27]]
          Source diagram or notation
        4. [[IMAGE:6f4499f0a9668d18_13_28]]
          Source diagram or notation

        A published solution is not available for this question yet.

        Question 21 MCQ · 2.0 marks

        Consider the following fixed neural network implemented in PyTorch. [[IMAGE:6f4499f0a9668d18_14_29]] Loss function used: [[IMAGE:6f4499f0a9668d18_14_30]] Based on the above data, answer the given subquestions.
        Given the input: [[IMAGE:6f4499f0a9668d18_14_31]] What is the output [[IMAGE:6f4499f0a9668d18_14_32]] produced by the network?
        Source diagram or notationSource diagram or notationSource diagram or notationSource diagram or notation
        1. 0.500
        2. 0.612
        3. 0.648
        4. 0.731

        A published solution is not available for this question yet.

        Question 22 MCQ · 2.0 marks

        Consider the following fixed neural network implemented in PyTorch. [[IMAGE:6f4499f0a9668d18_14_29]] Loss function used: [[IMAGE:6f4499f0a9668d18_14_30]] Based on the above data, answer the given subquestions.
        For the input: [[IMAGE:6f4499f0a9668d18_15_33]] The network output is: [[IMAGE:6f4499f0a9668d18_15_34]] Recall: [[IMAGE:6f4499f0a9668d18_15_35]] What is the gradient of the loss with respect to the **hidden layer activations** [[IMAGE:6f4499f0a9668d18_15_36]] (i.e. [[IMAGE:6f4499f0a9668d18_15_37]] )?
        Source diagram or notationSource diagram or notationSource diagram or notationSource diagram or notationSource diagram or notationSource diagram or notationSource diagram or notation
        1. [ 0.334, 0.334]
        2. [ 0.334, -0.334]
        3. [-0.334, 0.334]
        4. [ 0.111, -0.111]

        A published solution is not available for this question yet.

        Question 23 MSQ · 2.0 marks

        Consider the following fixed neural network implemented in PyTorch. [[IMAGE:6f4499f0a9668d18_14_29]] Loss function used: [[IMAGE:6f4499f0a9668d18_14_30]] Based on the above data, answer the given subquestions.
        Based on the **hidden-layer weights** and the **output-layer weights**, which of the following statements are **correct**?
        Source diagram or notationSource diagram or notation
        1. Hidden neuron 0 produces larger activations when [[IMAGE:6f4499f0a9668d18_15_38]] .
          Source diagram or notation
        2. Hidden neuron 0 produces larger activations when [[IMAGE:6f4499f0a9668d18_15_39]] .
          Source diagram or notation
        3. Hidden neuron 1 produces larger activations when [[IMAGE:6f4499f0a9668d18_15_40]] .
          Source diagram or notation
        4. If the predicted class is 1, then the hidden neuron 0 is highly activated.
        5. If the predicted class is 0, then the hidden neuron 0 is highly activated.
        6. If the predicted class is 0, then the hidden neuron 1 is highly activated.

        A published solution is not available for this question yet.