GCP - DE - Chapter 11 Exam Questions with
Answers
1. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Supervised learning algorithms are used to make
predictions. When an ML model is used to predict a
discrete value, 1 .
When a model is used to predict a continuous value, 2 . correct answer:
1 it is known as a classification model
2 it is known as a regression model
2. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
Supervised algorithms learn 1 .
Consider the data in Table 11.1, which contains information about
different kinds of animals. If you wanted to build an ML model to
predict whether or not an animal is a mammal, you could use data
such as that shown in the table.
Supervised learning algorithms use one of the columns of data
2 . For example, you
would use the Mammal column for the predicted value. In ML
terminology, this column is called a 3 correct answer: 1 from
examples
2 to represent the value to be predicted
3 label.
3. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
,The simplest form of a classifier is called a 1 .
A classifier that predicts if an animal is a mammal or not a mammal is
an example of a binary classifier.
More realistic examples of binary classifiers are those used to
predict if a credit card transaction is fraudulent or legitimate, and a
machine vision ML model that predicts if a medical image contains
or does not contain evidence of a malignant tumor. correct answer: 1
binary classifier
,4. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
A multiclass classification model assigns 1 .
In the animal data example, a model that predicts a habitat from the
other features is an example of a multiclass classifier.
Another example is a classifier that categorizes news stories into one of
several categories, such as politics, business, health, and technology.
correct answer: 1 more than two values
5. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
Some commonly used supervised algorithms are 1 . correct answer: 1
support vector machines (SVMs), decision trees, and logistic regression
6. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
Support vector machines (SVMs) represent 1 .
A simple example is a set of points in a three-
dimensional grid. SVMs find a boundary between
classes that 2 .
Figure 11.1 shows an example of a plane separating two groups of
instances. If a new point were added to the space, it could be
categorized based on which side of the plane it is located. correct answer: 1
instances in a multidimensional space
2 maximize the distance between those classes
7. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
In general, when features are numerical, you can imagine that each
instance is a 1 . Thinking of instances in terms of points located
, in space makes some useful concepts possible for thinking about
machine learning algorithms.
A decision boundary is a 2 . correct answer: 1 point in an n-dimensional space, where n is
the number of numerical features
Answers
1. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Supervised learning algorithms are used to make
predictions. When an ML model is used to predict a
discrete value, 1 .
When a model is used to predict a continuous value, 2 . correct answer:
1 it is known as a classification model
2 it is known as a regression model
2. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
Supervised algorithms learn 1 .
Consider the data in Table 11.1, which contains information about
different kinds of animals. If you wanted to build an ML model to
predict whether or not an animal is a mammal, you could use data
such as that shown in the table.
Supervised learning algorithms use one of the columns of data
2 . For example, you
would use the Mammal column for the predicted value. In ML
terminology, this column is called a 3 correct answer: 1 from
examples
2 to represent the value to be predicted
3 label.
3. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
,The simplest form of a classifier is called a 1 .
A classifier that predicts if an animal is a mammal or not a mammal is
an example of a binary classifier.
More realistic examples of binary classifiers are those used to
predict if a credit card transaction is fraudulent or legitimate, and a
machine vision ML model that predicts if a medical image contains
or does not contain evidence of a malignant tumor. correct answer: 1
binary classifier
,4. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
A multiclass classification model assigns 1 .
In the animal data example, a model that predicts a habitat from the
other features is an example of a multiclass classifier.
Another example is a classifier that categorizes news stories into one of
several categories, such as politics, business, health, and technology.
correct answer: 1 more than two values
5. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
Some commonly used supervised algorithms are 1 . correct answer: 1
support vector machines (SVMs), decision trees, and logistic regression
6. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
Support vector machines (SVMs) represent 1 .
A simple example is a set of points in a three-
dimensional grid. SVMs find a boundary between
classes that 2 .
Figure 11.1 shows an example of a plane separating two groups of
instances. If a new point were added to the space, it could be
categorized based on which side of the plane it is located. correct answer: 1
instances in a multidimensional space
2 maximize the distance between those classes
7. Three Types of Machine Learning
Algorithms SUPERVISED LEARNING
Classification
In general, when features are numerical, you can imagine that each
instance is a 1 . Thinking of instances in terms of points located
, in space makes some useful concepts possible for thinking about
machine learning algorithms.
A decision boundary is a 2 . correct answer: 1 point in an n-dimensional space, where n is
the number of numerical features
