Practice: Machine Learning Questions

The first 4 problems are all part of the same problem (they have the same setup text). Across those 4 problems, you should use each choice at most once.

The remaining problems are unrelated to the first 4.

Question 0

Consider the example used in the Visual Introduction to Machine Learning we read in the lesson today. For this problem, we will select one aspect of the example used in the article. We want you to select which of the vocabulary term we learned today best describes the role that aspect plays in the machine learning task.

The elevation of the house.

Your Task

Select one option. Write your answer down in your own space.

Option 0

Model

Option 1

Learning Algorithm

Option 2

Feature

Option 3

Label

Question 1

Consider the example used in the Visual Introduction to Machine Learning we read in the lesson today. For this problem, we will select one aspect of the example used in the article. We want you to select which of the vocabulary term we learned today best describes the role that aspect plays in the machine learning task.

The city the house is in (SF or NY).

Your Task

Select one option. Write your answer down in your own space.

Option 0

Model

Option 1

Learning Algorithm

Option 2

Feature

Option 3

Label

Question 2

Consider the example used in the Visual Introduction to Machine Learning we read in the lesson today. For this problem, we will select one aspect of the example used in the article. We want you to select which of the vocabulary term we learned today best describes the role that aspect plays in the machine learning task.

Growing the tree by adding forks.

Your Task

Select one option. Write your answer down in your own space.

Option 0

Model

Option 1

Learning Algorithm

Option 2

Feature

Option 3

Label

Question 3

Consider the example used in the Visual Introduction to Machine Learning we read in the lesson today. For this problem, we will select one aspect of the example used in the article. We want you to select which of the vocabulary term we learned today best describes the role that aspect plays in the machine learning task.

The final decision tree.

Your Task

Select one option. Write your answer down in your own space.

Option 0

Model

Option 1

Learning Algorithm

Option 2

Feature

Option 3

Label

Question 4

Warning

Note: This problem is not related to the previous ones!

Consider the task trying to take information about a patient and predicting their systolic blood pressure (one of the numbers that are reported in someone’s blood pressure).

Would this be best modeled by a classification or regression task?

Your Task

Select one option. Write your answer down in your own space.

Option 0

Classification

Option 1

Regression

Question 5

Consider the following decision tree (remember, left means true and right means false). Instead of giving the features names, we use generic names x[1] and x[2] .

We commonly think of a model’s decision boundary as being a drawing that shows how it separates all the points it predicts as one class from those that it predicts the other. Below we have shown a decision boundary separating the points classified as positive and those as negative.

Question: True or False, the decision boundary shown below corresponds to the decisions made by the tree shown above (i.e., the decisions shown in the graph for all possible inputs (x[1], x[2]) are consistent with the decisions for the tree)?

Your Task

Select one option. Write your answer down in your own space.

Option 0

True

Option 1

False