UNIT 3

What is the primary purpose of Decision Trees in machine learning?

• To cluster data points

• To perform linear regression

• To approximate discrete-valued target functions

• To approximate continuous-valued functions

Which algorithm is commonly associated with Decision Tree Learning?

• Naive Bayes

• Support Vector Machine

• ID3

• K-Means

What is a common issue faced when using Decision Trees?

• High computational cost

• Underfitting

• Overfitting

• Lack of interpretability

What does entropy measure in the context of Decision Trees?

• The depth of the tree

• The accuracy of the model

• The number of features in the dataset

• The disorder or impurity of a set of examples

Which of the following is a method to prevent overfitting in Decision Trees?

• Increasing the number of features

• Pruning

• Using a linear model

• Reducing the size of the dataset

What is the goal when picking a good split feature in Decision Trees?

• To maximize the number of branches

• To ensure all attributes are used

• To create subsets that are pure in a single class

• To minimize the depth of the tree

What does the term 'pruning' refer to in Decision Tree Learning?

• Increasing the training data

• Adding more nodes to the tree

• Changing the target function

• Removing unnecessary branches from the tree

Which of the following is NOT a characteristic of Decision Trees?

• They can represent disjunctive expressions

• They always produce the smallest possible tree

• They are easy to interpret

• They can handle both categorical and continuous data

What is the main advantage of representing learned trees as if-then rules?

• They are more complex

• They eliminate the need for training data

• They improve human readability

• They reduce computational time

In the context of Decision Trees, what does 'information gain' refer to?

• The total number of training examples

• The number of nodes in the tree

• The expected reduction in entropy from a split

• The increase in accuracy of the model