Multiclass Classification Quiz

What is multiclass classification used for?

• To identify outliers in the data

• To predict the exact value of a continuous variable

• To calculate probability values for a single class label

• To predict to which of multiple possible classes an observation belongs

In the penguin species example, how is the species encoded?

• 0: Adelie, 1: Gentoo, 2: Chinstrap

• Adelie, Gentoo, Chinstrap

• A: Adelie, G: Gentoo, C: Chinstrap

• 1: Adelie, 2: Gentoo, 3: Chinstrap

What are the two kinds of algorithms used to train a multiclass classification model?

• Binary classification algorithms and Decision tree algorithms

• Regression algorithms and Clustering algorithms

• Support Vector Machine (SVM) algorithms and K-Nearest Neighbors (KNN) algorithms

• One-vs-Rest (OvR) algorithms and Multinomial algorithms

What does a multinomial algorithm create?

• A binary classification function for each class label

• Multiple functions for each class label

• A single function that returns a multi-valued output

• A function that calculates the probability of the observation being a specific class

How is the confusion matrix for a multiclass classifier different from that of a binary classifier?

• It shows the number of predictions for each combination of predicted and actual class labels

• It only shows the true positive and true negative values

• It calculates the overall accuracy, recall, and precision metrics

• It displays the probability distribution for all possible classes

What is the overall accuracy of the multiclass classifier based on the given confusion matrix?

• 0.86

• 0.80

• 0.90

• 1.0

What is the overall recall of the multiclass classifier based on the given confusion matrix?

• 0.86

• 0.90

• 0.80

• 1.0

What is the overall precision of the multiclass classifier based on the given confusion matrix?

• 0.86

• 0.80

• 0.90

• 1.0

What is the overall F1-score of the multiclass classifier based on the given confusion matrix?

• 0.90

• 0.86

• 1.0

• 0.80

What kind of function does a multinomial algorithm create?

• A binary classification function for each class label

• A single function that returns a multi-valued output

• Multiple functions for each class label

• A function that calculates the probability of the observation being a specific class