Unit 1 & 2 - ML Quiz

Choose the correct option. Supervised learning is

• Task driven

• Data Driven

• Behavior driven

• Activity Driven

Testing the machine on all possible ways is

• Non Exhaustive Cross Validation

• Exhaustive Cross Validation

• Dimensionality reduction

• Feature Selection

Cross-validation helps to

• Judge how the trained model performs outside the sample on test data

• Assess the predictive performance of the models

• Reduce Dimensions

• Normalize Parameters

Identify which of the following features will take categorical values

• Person’s Age

• Price of house

• Persons Mother tongue

• Student mark

For the following confusion matrix find “Recall

• 0.73

• .78

• .8

• .7

Choose the correct  statement with respect to decision tree

• Decision tree is a linear classifier

• As we go down a decision tree, the entropy of a node decreases

• Information gain does not play any role in constructing decision tree

• An attribute with lower mutual information should be preferred to other attributes

. 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

• I only

• II only

• I and II only

• I, II and III     

Choose ALL the statements that are true for hierarchical agglomerative clustering

• The number of clusters need to be pre-specified

• The output of the clustering algorithm depends on output of similarity metric

• The number of merge operations does not depends on the number of clusters desired

• The number of merge operations depends on the characteristics of the data set

The distance metrics used in multivariate space is

• Euclidean Distance

• Mahalanobis Distance

• Cosine similarity

• Manhattan distance

____ clustering algorithm considers Probability for clustering data points

• Gaussian mixture model

• K -Means Clustering Algorithm

• Bayes Theorem

• Logistic Regression