Quiznetik

Machine Learning (ML) | Set 6

1. Let’s say, you are working with categorical feature(s) and you have not looked at the distribution of the categorical variable in the test data. You want to apply one hot encoding (OHE) on the categorical feature(s). What challenges you may face if you have applied OHE on a categorical variable of train dataset?

Correct : D. both a and b

2. Which of the following sentence is FALSE regarding regression?

Correct : D. it discovers causal relationships.

3. scikit-learn also provides functions for creating dummy datasets from scratch:

Correct : D. all above

4. which can accept a NumPy RandomState generator or an integer seed.

Correct : B. random_state

5. In many classification problems, the target dataset is made up of categorical labels which cannot immediately be processed by any algorithm. An encoding is needed and scikit-learn offers at least          valid options

Correct : B. 2

6. is the most drastic one and should be considered only when the dataset is quite large, the number of missing features is high, and any prediction could be risky.

Correct : A. removing the whole line

7. It's possible to specify if the scaling process must include both mean and standard deviation using the parameters                 .

Correct : C. both a & b

8. Which of the following selects the best K high-score features.

Correct : C. selectkbest

9. Suppose you have fitted a complex regression model on a dataset. Now, you are using Ridge regression with tuning parameter lambda to reduce its complexity. Choose the option(s) below which describes relationship of bias and variance with lambda.

Correct : C. in case of very large lambda; bias is high, variance is low

10. What is/are true about ridge regression? 1. When lambda is 0, model works like linear regression model 2. When lambda is 0, model doesn’t work like linear regression model 3. When lambda goes to infinity, we get very, very small coefficients approaching 0 4. When lambda goes to infinity, we get very, very large coefficients approaching infinity

Correct : A. 1 and 3

11. Which of the following method(s) does not have closed form solution for its coefficients?

Correct : B. lasso

12. Function used for linear regression in R is

Correct : A. lm(formula, data)

13. In the mathematical Equation of Linear Regression Y = β1 + β2X + ϵ, (β1, β2) refers to

Correct : C. (y-intercept, slope)

14. Suppose that we have N independent variables (X1,X2… Xn) and dependent variable is Y. Now Imagine that you are applying linear regression by fitting the best fit line using least square error on this data. You found that correlation coefficient for one of it’s variable(Say X1) with Y is -0.95.Which of the following is true for X1?

Correct : B. relation between the x1 and y is strong

15. We have been given a dataset with n records in which we have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To test our linear regressor, we split the data in training set and test set randomly. Now we increase the training set size gradually. As the training set size increases, what do you expect will happen with the mean training error?

Correct : D. can’t say

16. We have been given a dataset with n records in which we have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To test our linear regressor, we split the data in training set and test set randomly. What do you expect will happen with bias and variance as you increase the size of training data?

Correct : D. bias increases and variance decreases

17. Suppose, you got a situation where you find that your linear regression model is under fitting the data. In such situation which of the following options would you consider?1. I will add more variables2. I will start introducing polynomial degree variables3. I will remove some variables

Correct : A. 1 and 2

18. Problem: Players will play if weather is sunny. Is this statement is correct?

Correct : A. true

19. Multinomial Naïve Bayes Classifier is     _                distribution

Correct : B. discrete

20. For the given weather data, Calculate probability of not playing

Correct : C. 0.36

21. The minimum time complexity for training an SVM is O(n2). According to this fact, what sizes of datasets are not best suited for SVM’s?

Correct : A. large datasets

22. The effectiveness of an SVM depends upon:

Correct : D. all of the above

23. What do you mean by generalization error in terms of the SVM?

Correct : B. how accurately the svm can predict outcomes for unseen data

24. We usually use feature normalization before using the Gaussian kernel in SVM. What is true about feature normalization? 1. We do feature normalization so that new feature will dominate other 2. Some times, feature normalization is not feasible in case of categorical variables3. Feature normalization always helps when we use Gaussian kernel in SVM

Correct : B. 1 and 2

25. Support vectors are the data points that lie closest to the decision surface.

Correct : A. true

26. Which of the following is not supervised learning?

Correct : A. pca

27. Gaussian Naïve Bayes Classifier is     _                distribution

Correct : A. continuous

28. If I am using all features of my dataset and I achieve 100% accuracy on my training set, but ~70% on validation set, what should I look out for?

Correct : C. overfitting

29. What is the purpose of performing cross- validation?

Correct : C. both a and b

30. Suppose you are using a Linear SVM classifier with 2 class classification problem. Now you have been given the following data in which some points are circled red that are representing support vectors.If you remove the following any one red points from the data. Does the decision boundary will change?

Correct : A. yes

31. Linear SVMs have no hyperparameters that need to be set by cross-validation

Correct : B. false

32. For the given weather data, what is the probability that players will play if weather is sunny

Correct : D. 0.6

33. 100 people are at party. Given data gives information about how many wear pink or not, and if a man or not. Imagine a pink wearing guest leaves, what is the probability of being a man

Correct : B. 0.2

34. Problem: Players will play if weather is sunny. Is t

Correct : A. true

35. For the given weather data, Calculate probability

Correct : B. 0.64

36. For the given weather data, Calculate probability

Correct : C. 0.36

37. For the given weather data, what is the probabilit

Correct : D. 0.6

38. 100 people are at party. Given data gives informa

Correct : B. 0.2

39. 100 people are at party. Given data gives informa

Correct : A. true

40. What do you mean by generalization error in terms of the SVM?

Correct : B. how accuratel

41. The effectiveness of an SVM depends upon:

Correct : D. all of the abov

42. Support vectors are the data points that lie closest to the decision

Correct : A. true

43. The SVM’s are less effective when:

Correct : C. the data is noisy and contains

44. Suppose you are using RBF kernel in SVM with high Gamma valu

Correct : B. uthe model wo

45. The cost parameter in the SVM means:

Correct : C. the tradeoff between misclassificati on and simplicity of the model

46. If I am using all features of my dataset and I achieve 100% accura

Correct : C. overfitting

47. Which of the following are real world applications of the SVM?

Correct : D. all of the abov

48. Suppose you have trained an SVM with linear decision boundary after training SVM, you correctly infer that your SVM model is under fitting.Which of the following option would you more likely to consider iterating SVM next time?

Correct : C. you will try to c

49. We usually use feature normalization before using the Gaussian k

Correct : B. 1 and 2

50. Linear SVMs have no hyperparameters that need to be set by cross-valid

Correct : B. false

51. In a real problem, you should check to see if the SVM is separable and th

Correct : B. false

52. In reinforcement learning, this feedback is usually called as .

Correct : C. reward

53. In the last decade, many researchers started training bigger and bigger models, built with several different layers that's why this approach is called .

Correct : A. deep learning

54. When it is necessary to allow the model to develop a generalization ability and avoid a common problem called .

Correct : A. overfitting

55. Techniques involve the usage of both labeled and unlabeled data is called .

Correct : B. semi- supervised

56. Reinforcement learning is particularly efficient when .

Correct : D. all above

57. During the last few years, many algorithms have been applied to deep neural networks to learn the best policy for playing Atari video games and to teach an agent how to associate the right action with an input representing the state.

Correct : D. none of above

58. if there is only a discrete number of possible outcomes (called categories), the process becomes a .

Correct : B. classification.

59. Let’s say, you are working with categorical feature(s) and you have not looked at the distribution of the categorical variable in the test data. You want to apply one hot encoding (OHE) on the categorical feature(s). What challenges you may face if you have applied OHE on a categorical variable of train dataset?

Correct : D. both a and b

60. scikit-learn also provides functions for creating dummy datasets from scratch:

Correct : D. all above

61. which can accept a NumPy RandomState generator or an integer seed.

Correct : B. random_state

62. In many classification problems, the target dataset is made up of categorical labels which cannot immediately be processed by any algorithm. An encoding is needed and scikit-learn offers at least valid options

Correct : B. 2

63. It's possible to specify if the scaling process must include both mean and standard deviation using the parameters .

Correct : C. both a & b

64. Which of the following selects the best K high-score features.

Correct : C. selectkbest

65. We have been given a dataset with n records in which we have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To test our linear regressor, we split the data in training set and test set randomly. Now we increase the training set size gradually. As the training set size increases, what do you expect will happen with the mean training error?

Correct : D. can’t say

66. We have been given a dataset with n records in which we have input attribute as x and output attribute as y. Suppose we use a linear regression method to model this data. To test our linear regressor, we split the data in training set and test set randomly. What do you expect will happen with bias and variance as you increase the size of training data?

Correct : D. bias increases and variance decreases

67. Problem: Players will play if weather is sunny. Is this statement is correct?

Correct : A. true

68. Multinomial Naïve Bayes Classifier is     _ distribution

Correct : B. discrete

69. The minimum time complexity for training an SVM is O(n2). According to this fact, what sizes of datasets are not best suited for SVM’s?

Correct : A. large datasets

70. We usually use feature normalization before using the Gaussian kernel in SVM. What is true about feature normalization? 1. We do feature normalization so that new feature will dominate other 2. Some times, feature normalization is not feasible in case of categorical variables3. Feature normalization always helps when we use Gaussian kernel in SVM

Correct : B. 1 and 2

71. Which of the following is not supervised learning?

Correct : A. pca

72. Gaussian Naïve Bayes Classifier is     _ distribution

Correct : A. continuous

73. If I am using all features of my dataset and I achieve 100% accuracy on my training set, but ~70% on validation set, what should I look out for?

Correct : C. overfitting

74. The cost parameter in the SVM means:

Correct : C. the tradeoff between misclassificati on and simplicity of the model

75. We usually use feature normalization before using the Gaussian k

Correct : B. 1 and 2

76. The effectiveness of an SVM depends upon:

Correct : D. all of the above

77. The process of forming general concept definitions from examples of concepts to be learned.

Correct : C. induction

78. Computers are best at learning

Correct : A. facts.

79. Data used to build a data mining model.

Correct : B. training data

80. Supervised learning and unsupervised clustering both require at least one

Correct : A. hidden attribute.

81. Supervised learning differs from unsupervised clustering in that supervised learning requires

Correct : B. input attributes to be categorical.

82. A regression model in which more than one independent variable is used to predict the dependent variable is called

Correct : C. an independent model

83. A term used to describe the case when the independent variables in a multiple regression model are correlated is

Correct : C. multicollinearity

84. A multiple regression model has the form: y = 2 + 3x1 + 4x2. As x1 increases by 1 unit (holding x2 constant), y will

Correct : C. increase by 4 units

85. A multiple regression model has

Correct : B. more than one dependent variable

86. A measure of goodness of fit for the estimated regression equation is the

Correct : C. mean square due to regression

87. The adjusted multiple coefficient of determination accounts for

Correct : D. none of the above

88. The multiple coefficient of determination is computed by

Correct : C. dividing sst by sse

89. For a multiple regression model, SST = 200 and SSE = 50. The multiple coefficient of determination is

Correct : B. 4.00

90. A nearest neighbor approach is best used

Correct : B. when irrelevant attributes have been removed from the data.

91. Another name for an output attribute.

Correct : B. independent variable

92. Classification problems are distinguished from estimation problems in that

Correct : C. classification problems do not allow an output attribute.

93. Which statement is true about prediction problems?

Correct : D. the resultant model is designed to classify current behavior.

94. Which of the following is a common use of unsupervised clustering?

Correct : A. detect outliers

95. The average positive difference between computed and desired outcome values.

Correct : D. mean positive error

96. Selecting data so as to assure that each class is properly represented in both the training and test set.

Correct : B. stratification

97. The standard error is defined as the square root of this computation.

Correct : A. the sample variance divided by the total number of sample instances.

98. Data used to optimize the parameter settings of a supervised learner model.

Correct : D. validation

99. Bootstrapping allows us to

Correct : A. choose the same training instance several times.

100. The correlation coefficient for two real-valued attributes is –0.85. What does this value tell you?

Correct : C. as the value of one attribute decreases the value of the second attribute increases.