AML Quiz 4 Section B

10 Questions | Total Attempts: 50

SettingsSettingsSettings
Please wait...
AML Quiz 4 Section B

.


Questions and Answers
  • 1. 
    For the given set of points which of the following lines is most suitable to be the decision boundary?
    • A. 

      Option 1

    • B. 

      Option 2

    • C. 

      Option 3

    • D. 

      Option 4

  • 2. 
    Which of the following is/are true about the Perceptron classifier? (Choose multiple option)
    • A. 

      It can learn a OR function

    • B. 

      It can learn a AND function

    • C. 

      The obtained separating hyperplane depends on the order in which the points are presented in the training process.

    • D. 

      For a linearly separable problem, there exists some initialization of the weights which might lead to non-convergent cases.

  • 3. 
    Suppose you run K-means clustering algorithm on a given dataset. What are the factors on which the final clusters depend on ? I. The value of K II. The initial cluster seeds chosen III. The distance function used.
    • A. 

      I only

    • B. 

      II only

    • C. 

      I & II only

    • D. 

      I,II and III

  • 4. 
    After training an SVM, we can discard all examples which do not support vectors and can still classify new examples?
    • A. 

      True

    • B. 

      False

  • 5. 
    If g(z) is the sigmoid function, then its derivative with respect to z may be written in term of g(z) as
    • A. 

      G(z)(1-g(z))

    • B. 

      G(z)(1+g(z))

    • C. 

      -g(z)(1+g(z))

    • D. 

      G(z)(g(z)-1)

  • 6. 
    The back-propagation learning algorithm applied to a two layer neural network
    • A. 

      Always finds the globally optimal solution

    • B. 

      Finds a locally optimal solution which may be globally optimal.

    • C. 

      Never finds the globally optimal solution.

    • D. 

      Finds a locally optimal solution which is never globally optimal

  • 7. 
    Which of the following is true?
    • A. 

      In batch gradient descent we update the weights and biases of the neural network after forward pass over each training example.

    • B. 

      In batch gradient descent we update the weights and biases of our neural network after forward pass over all the training examples.

    • C. 

      Each step of stochastic gradient descent takes more time than each step of batch gradient descent.

    • D. 

      None of these three options is correct

  • 8. 
    In a neural network, which one of the following techniques is NOT useful to reduce overfitting?
    • A. 

      Dropout

    • B. 

      Regularization

    • C. 

      Batch normalizatioh

    • D. 

      Adding more layers

  • 9. 
    For an image recognition problem (such as recognizing a cat in a photo), which architecture of neural network has been found to be better suited for the tasks
    • A. 

      Multi layer perceptron

    • B. 

      Recurrent neural network

    • C. 

      Convolutional neural network

    • D. 

      Perceptron

  • 10. 
    The Bayes Optimal Classifier
    • A. 

      Is an ensemble of some selected hypotheses in the hypothesis space

    • B. 

      Is an ensemble of all the hypotheses in the hypothesis space

    • C. 

      Is the hypothesis that gives best result on test instances

    • D. 

      None of the above

Back to Top Back to top