Machine Learning MCQ



Question 31 : Let us implement a single neuron with threshold activation function to simulate working of logical AND gate.Give the correct values of weights and threshold.

  1. w1=1,w2=-1,T=-1
  2. w1=-1,w2=-1,T=-1
  3. w1=1,w2=1,T=2
  4. w1=-1,w2=1,T=-2
  

Question 32 : The amount of output of one unit received by another unit depends on what?

  1. output unit
  2. input unit
  3. activation value
  4. weight
  

Question 33 : Negative sign of weight indicates?

  1. excitatory input
  2. inhibitory input
  3. excitatory output
  4. inhibitory output
  

Question 34 : The average positive difference between computed and desired outcome values.

  1. root mean squared error
  2. mean squared error
  3. mean absolute error
  4. mean positive error
  

Question 35 : Multiple regression model has

  1. Only one independent variable
  2. More than one dependent variables
  3. More than one independent variables
  4. Only one dependent variable
  

Question 36 : Given a large dataset of medical records from patients suffering from heart disease, try to learn whether there might be different clusters of such patients for which we might tailor separate treatments. What kind of learning problem is this?

  1. Supervised learning
  2. Unsupervised learning
  3. Reinforcement learning
  4. Semi-Supervised Learning
  

Question 37 : Which of the following is not example of Derivative free optimization

  1. Random Search Method
  2. Downhill simplex method
  3. Genetic algorithm
  4. Steepest Descent
  

Question 38 : You are given a labeled binary classification data set with N data points and D features. Suppose that N < D. In training an SVM on this data set, which of the following kernels is likely to be most appropriate?

  1. Linear kernel
  2. Quadratic kernel
  3. Higher-order polynomial kernel
  4. RBF kernel
  

Question 39 : A and B are two events. If P(A, B) decreases while P(A) increases, which of the following is true?

  1. P(A|B) decreases
  2. P(B|A) decreases
  3. P(B) decreases
  4. P(B|A) increases
  

Question 40 : What is the approach of the basic algorithm for decision tree induction?

  1. Greedy
  2. Bottom up
  3. Procedural
  4. Step by Step
  

Question 41 : Which of the following techniques would perform worst for reducing dimensions of a data set?

  1. Removing columns which have high variance in data
  2. Removing columns which have too many missing values
  3. Removing columns with redundant data
  4. Removing columns with similar data trends
  

Question 42 : Which algorithm is State Transition Based Algorithm?

  1. K-Nearest neighbor
  2. Hidden markov model
  3. Bayes theorem
  4. Linear regression
  

Question 43 : Which of the following is not supervised learning algorithm

  1. PCA
  2. Decision Tree
  3. Bayes Theorem
  4. Linear regression
  

Question 44 : What is the major component of PCA?

  1. all the eigen vectors for the projection space
  2. The average of eigen vectors for the projection space
  3. Value of the last among the eigen vectors for the projection space
  4. Value of the first among the eigen vectors for the projection space
  

Question 45 : Which of the following option(s) is / are true? 1.You need to randomize parameters in PCA 2.You don’t need to randomize parameters in PCA 3.PCA can be trapped into local maxima problem 4.PCA can’t be trapped into local minima problem

  1. 1 and 3
  2. 1 and 4
  3. 2 and 3
  4. 2 and 4
  

Question 46 : Predicting on whether it will rain or not tomorrow evening at a particular time is a type of _________ problem.

  1. Clustering
  2. Regression
  3. Unsupervised learning
  4. Supervised learning
  

Question 47 : Which of the following is a disadvantage of decision trees?

  1. Decision trees require less preprocessing.
  2. Decision trees are robust to outliers.
  3. Decision trees are prone to be overfit.
  4. Decision tree traces all possible alternatives.
  

Question 48 : A machine learning model gives 95% accuracy on an unbalanced dataset. What can be concluded about the classifier?

  1. Since accuracy is 95% the classifier will perform well in real life scenario
  2. Classifier will give good accuracy on the validation of the dataset.
  3. Unbalanced Dataset will not affect the performance of classifier
  4. Because of an unbalanced dataset the classifier will predict only one class of samples accurately.
  

Question 49 : You ran gradient descent for 20 iterations with learning rate=0.2 and compute cost for each iteration. You observe that cost decreases after each iteration. Based on this which conclusion is more suitable.

  1. 0.2 is an effective choice of learning rate.
  2. Try larger values of learning rate like 1.
  3. 0.2 is not an effective choice of learning rate.
  4. The model is overfitting.
  

Question 50 : Which statement is true about regression problems?

  1. Output attribute must be only categorical.
  2. Output attribute must be only numerical
  3. Output attribute can be either categorical or numerical.
  4. Output attribute can be neither categorical nor numerical.
  
  • chevron_left
  • 1
  • 2
  • chevron_right