MauryaHub PYQ Practice

cs3004_2024T2_Q1_NA.pdf

Deep Learning · Quiz 1 · May 2024

← 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 43 NAT · 3.0 marks

[[IMAGE:54eb6177597e41d5_2_0]]
Source diagram or notation

    A published solution is not available for this question yet.

    Question 44 NAT · 3.0 marks

    [[IMAGE:54eb6177597e41d5_3_1]]
    Source diagram or notation

      A published solution is not available for this question yet.

      Question 45 NAT · 3.0 marks

      [[IMAGE:54eb6177597e41d5_4_2]]
      Source diagram or notation

        A published solution is not available for this question yet.

        Question 46 MCQ · 3.0 marks

        [[IMAGE:54eb6177597e41d5_4_3]]
        Source diagram or notation
        1. YES
        2. NO

        A published solution is not available for this question yet.

        Question 47 MCQ · 3.0 marks

        As per gradient descent, we should move towards 180 degrees with respect to gradient direction. What will happen if we move between 90 and 180 degrees? Consider the loss function to be convex.
        1. The loss function will increase.
        2. The loss function will decrease, although not to the maximum possible extent.
        3. The loss function will remain the same.
        4. Can’t say. It depends on other parameters of the convex function.

        A published solution is not available for this question yet.

        Question 48 MCQ · 3.0 marks

        Which of the following best describes the objective of gradient descent in relation to the Taylor series expansion of a function f(x) around a given point x0?
        1. Gradient descent aims to minimize the first-order term of the Taylor series expansion to approximate the function f(x) globally.
        2. Gradient descent seeks to minimize the first-order term of the Taylor series expansion to efficiently navigate the local neighborhood around the given point x0.
        3. Gradient descent utilizes the entire Taylor series expansion to approximate the function f(x) and find its global minimum.

        A published solution is not available for this question yet.

        Question 49 MCQ · 2.0 marks

        Any boolean function of n inputs can be represented exactly by a network of perceptrons containing at least ____________ hidden layer(s) with at least ___________ perceptrons (each) and one output layer containing one perceptron.
        1. [[IMAGE:54eb6177597e41d5_5_4]]
          Source diagram or notation
        2. [[IMAGE:54eb6177597e41d5_6_5]]
          Source diagram or notation
        3. [[IMAGE:54eb6177597e41d5_6_6]]
          Source diagram or notation
        4. [[IMAGE:54eb6177597e41d5_6_7]]
          Source diagram or notation

        A published solution is not available for this question yet.

        Question 50 MCQ · 5.0 marks

        Consider the plot shown below: [[IMAGE:54eb6177597e41d5_6_8]] Which of the following could be the correct equation for this plot?
        Source diagram or notation
        1. [[IMAGE:54eb6177597e41d5_6_9]]
          Source diagram or notation
        2. [[IMAGE:54eb6177597e41d5_6_10]]
          Source diagram or notation
        3. [[IMAGE:54eb6177597e41d5_6_11]]
          Source diagram or notation
        4. [[IMAGE:54eb6177597e41d5_7_12]]
          Source diagram or notation

        A published solution is not available for this question yet.

        Question 51 MSQ · 3.0 marks

        Consider the MP neuron model and its applicability to representing boolean functions. Select the correct statements:
        1. The MP neuron model can represent a wide range of boolean functions (not all) by appropriately adjusting its weights and thresholds.
        2. The MP neuron model can approximate arbitrary boolean functions, including non-linear ones.
        3. The MP neuron model can accurately represent the XOR function by adjusting its weights and thresholds.
        4. The representation power of the MP neuron model increases when multiple neurons are combined in a network architecture.

        A published solution is not available for this question yet.

        Question 52 NAT · 2.0 marks

        Consider a feed-forward neural network shown below [[IMAGE:54eb6177597e41d5_8_13]] Based on the above data, answer the given subquestions.
        What is the total number of parameters (excluding bias) in the network?
        Source diagram or notation

          A published solution is not available for this question yet.

          Question 53 NAT · 2.0 marks

          Consider a feed-forward neural network shown below [[IMAGE:54eb6177597e41d5_8_13]] Based on the above data, answer the given subquestions.
          [[IMAGE:54eb6177597e41d5_8_14]]
          Source diagram or notationSource diagram or notation

            A published solution is not available for this question yet.

            Question 54 NAT · 2.0 marks

            Consider a feed-forward neural network shown below [[IMAGE:54eb6177597e41d5_8_13]] Based on the above data, answer the given subquestions.
            [[IMAGE:54eb6177597e41d5_9_15]]
            Source diagram or notationSource diagram or notation

              A published solution is not available for this question yet.

              Question 55 MCQ · 4.0 marks

              [[IMAGE:54eb6177597e41d5_9_16]]
              Source diagram or notation
              1. 0.09
              2. 0.06
              3. 0.001
              4. 0.0001

              A published solution is not available for this question yet.

              Question 56 MCQ · 4.0 marks

              Assume you are using mini-batch gradient descent with a total dataset size of 1,000 and a batch size of 20. If you process 10,000 mini-batches, how many epochs have been completed?
              1. 5 epochs
              2. 10 epochs
              3. 20 epochs
              4. 200 epochs

              A published solution is not available for this question yet.

              Question 57 MCQ · 4.0 marks

              If the batch size in mini-batch gradient descent is increased from 32 to 128 while keeping all other parameters constant, what is the likely impact on the variance of the gradient estimates per update?
              1. Increases the variance
              2. Decreases the variance
              3. No impact on the variance
              4. Initially decreases then increases the variance

              A published solution is not available for this question yet.

              Question 58 MCQ · 4.0 marks

              What do contour lines on a contour plot represent?
              1. The areas where the function value increases most rapidly
              2. Lines connecting points where the function has the same output value
              3. The maximum and minimum values of a function
              4. The gradient of the function at those points       **Data Viz** **Section Id :** 64065359427

              A published solution is not available for this question yet.