Quiz 3

Question 1

Decision trees are an algorithm for which machine learning task?

Answer 1

Classification

Question 2

Root node

Answer 2

decision tree has no incoming edges and zero or more outgoing edges

Question 3

Internal node

Answer 3

has more than one incoming edge and one or more outgoing edges

Question 4

Terminal node

Answer 4

has exactly one incoming edge and no outgoing edge

Question 5

Internal node

Answer 5

denotes a test on a feature

Question 6

In classification, a model or classifier

Answer 6

constructed to predict class (categorical) labels

Question 7

Homogeneous class distribution

Answer 7

preferred to determine the best split for decision trees

Question 8

Methods to look at node Impurity

Answer 8

Gini Index
Information Gain
Gain Ratio
Misclassification Error

Question 9

What is the minimum and maximum value for entropy?

Answer 9

0,1

Question 10

What is the minimum and maximum value of GINI?

Answer 10

0,0.5

Question 11

What is the minimum and maximum value for Misclassification Error?

Answer 11

0,0.5

Question 12

The process of building a decision tree is recursive. It is built one node at a time and the algorithm is applied at each node the same way.

Answer 12

True

Question 13

During the process of building a decision tree, at each node, the algorithm decides which attribute to use for a new split based on some criteria evaluated for each possible attribute.

Answer 13

True

Question 14

During the process of building a decision tree, at each node, we consider the similarities between all the points and take the most similar ones to create the next nodes based on a criteria evaluated at each similar group of data.

Answer 14

False

Question 15

What are splitting criteria used in decision trees?

Answer 15

GINI index
Information Gain - Entropy
Misclassification Error
Gain Ratio

Question 16

Building a tree that is too large or complex can cause

Answer 16

overfitting

Question 17

To reduce the size of a tree after it is built, use an algorithm for

Answer 17

pruning

Question 18

A decision tree tells how to classify instances. It can be turned into a list of rules. Which of the following are true?

Answer 18

Each leaf node gets turned into one rule

Each internal node after the root gets added to the rule as an and condition

Question 19

Overfitting in Machine Learning is defined as when a statistical model describes random error or noise instead of underlying relationship or when a model is excessively complex.

Answer 19

True