Machine Learning MCQ Multiple Choice Questions Answers - Page 2 for Practice
31. You observe the following while fitting a linear regression to the data: As you increase the amount of training data, the test error decreases and the training error increases. The train error is quite low (almost what you expect it to), while the test error is much higher than the train error. What do you think is the main reason behind this behavior. Choose the most probable option.
Correct Answer is: High variance
32. A measure of goodness of fit for the estimated regression equation is the
Correct Answer is: mean square due to regression
33. A nearest neighbor approach is best used
Correct Answer is: when irrelevant attributes have been removed from the data.
34. A regression model in which more than one independent variable is used to predict the dependent variable is called
Correct Answer is: an independent model
35. A term used to describe the case when the independent variables in a multiple regression model are correlated is
Correct Answer is: multicollinearity
36. Adding more basis functions in a linear model... (pick the most probably option)
Correct Answer is: Decreases model bias
37. Another name for an output attribute.
Correct Answer is: independent variable
38. Bootstrapping allows us to
Correct Answer is: choose the same training instance several times.
39. Choose the options that are correct regarding machine learning (ML) and artificial intelligence (AI),(A) ML is an alternate way of programming intelligent machines.(B) ML and AI have very different goals.(C) ML is a set of techniques that turns a dataset into a software.(D) AI is a software that can emulate the human mind.
Correct Answer is: (A), (C), (D)
40. Classification problems are distinguished from estimation problems in that
Correct Answer is: classification problems do not allow an output attribute.
41. Computational complexity of Gradient descent is
Correct Answer is: polynomial in D
42. Computers are best at learning
Correct Answer is: facts.
43. Consider a binary classification problem. Suppose I have trained a model on a linearly separable training set, and now I get a new labeled data point which is correctly classified by the model, and far away from the decision boundary. If I now add this new point to my earlier training set and re-train, in which cases is the learnt decision boundary likely to change?
Correct Answer is: When my model is logistic regression and Gaussian discriminant analysis.
44. Data used to build a data mining model.
Correct Answer is: training data
45. Data used to optimize the parameter settings of a supervised learner model.
Correct Answer is: validation
46. Generalization error measures how well an algorithm perform on unseen data. The test error obtained using cross-validation is an estimate of the generalization error. Is this estimate unbiased?
Correct Answer is: No
47. Grid search is
Correct Answer is: Exponential in D and Linear in N
48. K-fold cross-validation is
Correct Answer is: linear in K
49. Let us say that we have computed the gradient of our cost function and stored it in a vector g. What is the cost of one gradient descent update given the gradient?
Correct Answer is: O(D)
50. Logistic regression is a ........... regression technique that is used to model data having a ........... outcome.
Correct Answer is: nonlinear, binary
51. Machine learning techniques differ from statistical techniques in that machine learning methods
Correct Answer is: are better able to deal with missing and noisy data.
52. Regarding bias and variance, which of the follwing statements are true? (Here high and low are relative to the ideal model)
Correct Answer is: Models which overfit have a low bias and underfit have a low variance.
53. A multiple regression model has
Correct Answer is: more than one dependent variable
