MauryaHub PYQ Practice

cs3004_2023T2_Q1_NA.pdf

Deep Learning · Quiz 1 · May 2023

← Course papers · Start practice / exam

This page contains the reliably extracted subset, not the complete original paper.

Questions and published explanations below are available without starting a test. Some questions may not have a published solution yet.

Question 41 MSQ · 3.0 marks

[[IMAGE:e3d2e612e6c63e02_3_0]]
Source diagram or notation
  1. There exists at least one function for which MP neuron can not find a threshold such that it produces zero error.
  2. One can manually find the threshold such that MP neuron produces zero classification error for all possible functions.
  3. There exist at least 4 boolean functions such that MP neuron can represent them with zero classification error.
  4. MP neuron must have at least one inhibitory input to implement all possible boolean functions.

A published solution is not available for this question yet.

Question 42 MCQ · 3.0 marks

[[IMAGE:e3d2e612e6c63e02_4_1]]
Source diagram or notation
  1. True
  2. False
  3. Insufficient information
  4. Not possible to decide

A published solution is not available for this question yet.

Question 43 NAT · 3.0 marks

[[IMAGE:e3d2e612e6c63e02_5_2]] Based on the above data, answer the given subquestions.
[[IMAGE:e3d2e612e6c63e02_5_3]]
Source diagram or notationSource diagram or notation

    A published solution is not available for this question yet.

    Question 44 NAT · 2.0 marks

    [[IMAGE:e3d2e612e6c63e02_5_2]] Based on the above data, answer the given subquestions.
    How many points were correctly classified?
    Source diagram or notation

      A published solution is not available for this question yet.

      Question 45 NAT · 4.0 marks

      [[IMAGE:e3d2e612e6c63e02_5_2]] Based on the above data, answer the given subquestions.
      Update the weight values using the perceptron learning algorithm by visiting the following points in order (x4, x3). What is the angle (in degrees) between the updated weight vector and the initial weight vector?
      Source diagram or notation

        A published solution is not available for this question yet.

        Question 46 MCQ · 3.0 marks

        [[IMAGE:e3d2e612e6c63e02_5_2]] Based on the above data, answer the given subquestions.
        [[IMAGE:e3d2e612e6c63e02_7_4]]
        Source diagram or notationSource diagram or notation
        1. True
        2. False
        3. Insufficient information to conclude

        A published solution is not available for this question yet.

        Question 47 NAT · 5.0 marks

        [[IMAGE:e3d2e612e6c63e02_8_5]]
        Source diagram or notation

          A published solution is not available for this question yet.

          Question 48 MCQ · 4.0 marks

          Look at the contours of a hill shown below. Suppose a person walks from location A to location C via location B. Then choose the correct statements from the following list of statements [[IMAGE:e3d2e612e6c63e02_9_6]]
          Source diagram or notation
          1. The person has to do one steep ascending and one steep descending
          2. The person has to do two steep ascending and two steep descending
          3. The person has to do one steep ascending and two steep descending
          4. The person has to do two steep ascending and one steep descending

          A published solution is not available for this question yet.

          Question 49 NAT · 4.0 marks

          Consider a neural network with three hidden layers and one output layer. The hidden layers contain 100 neurons each. Suppose we have a square image of size 30×30 containing either a cat (positive class) or a dog (negative class). The neural network is designed to recognize it by outputting a probability score for each class. The input image is flattened into an array of size 900. Assume that all neurons in the network have bias associated with them and use the sigmoid activation function. How many parameters are there in the network?

            A published solution is not available for this question yet.

            Question 50 NAT · 5.0 marks

            [[IMAGE:e3d2e612e6c63e02_11_7]] Based on the above data, answer the given subquestions.
            [[IMAGE:e3d2e612e6c63e02_12_8]]
            Source diagram or notationSource diagram or notation

              A published solution is not available for this question yet.

              Question 51 NAT · 5.0 marks

              [[IMAGE:e3d2e612e6c63e02_11_7]] Based on the above data, answer the given subquestions.
              [[IMAGE:e3d2e612e6c63e02_13_9]]
              Source diagram or notationSource diagram or notation

                A published solution is not available for this question yet.

                Question 52 NAT · 5.0 marks

                [[IMAGE:e3d2e612e6c63e02_11_7]] Based on the above data, answer the given subquestions.
                [[IMAGE:e3d2e612e6c63e02_14_10]]
                Source diagram or notationSource diagram or notation

                  A published solution is not available for this question yet.

                  Question 53 NAT · 2.0 marks

                  Suppose that a team solves a 1000-class classification problem using a neural network that contains 32 layers. Assume that the training set contains exactly 32 samples per class. The team creates batches of samples, each of size 32. The batch is created such that all the samples in a batch belongs to the same class. Based on the above data, answer the given subquestions.
                  Suppose that the team trains the neural network with the given configuration using mini-batch Gradient Descent algorithm for 32 epochs. Then how many times do the parameters of the network get updated?

                    A published solution is not available for this question yet.

                    Question 54 NAT · 2.0 marks

                    Suppose that a team solves a 1000-class classification problem using a neural network that contains 32 layers. Assume that the training set contains exactly 32 samples per class. The team creates batches of samples, each of size 32. The batch is created such that all the samples in a batch belongs to the same class. Based on the above data, answer the given subquestions.
                    Suppose we use SGD (Stochastic Gradient Descent) algorithm to update the parameters of the network by running it for 32 epochs. Then how many times do the parameters of the network get updated?

                      A published solution is not available for this question yet.