Quiz on Support Vector Machine

What is the primary objective of a Support Vector Machine (SVM) algorithm?

• Minimize the distance between data points and the decision boundary.

• Maximize the variance of the data within each class.

• Find the hyperplane with the maximum margin between classes.

• Reduce the number of features in the data.

Which type of machine learning problem is SVMs primarily designed for?

• Unsupervised learning

• Supervised classification

• Supervised regression

• Reinforcement learning

What are the points that define the margin in an SVM?

• All data points in the training set.

• Randomly chosen data points.

• Data points closest to the hyperplane from each class.

• All data points on the decision boundary.

What is the main advantage of SVMs?

• High interpretability of the model.

• Good performance in high-dimensional spaces with limited data.

• Ability to handle complex, non-linear relationships.

• Fast training time for large datasets.

What is the main disadvantage of SVMs?

• Sensitive to parameter tuning and can be computationally expensive for large datasets.

• Prone to overfitting on small datasets.

• Not suitable for tasks with multiple class labels.

• Difficult to interpret the decision-making process.

What is the kernel trick used for in SVMs?

• o reduce the dimensionality of the data.

• To map data points to a higher dimensional space for better separation.

• To calculate the distance between data points efficiently.

• To improve the interpretability of the model.

What are the common types of kernel functions used in SVMs?

• Decision trees and random forests.

• K-means clustering and DBSCAN.

• Principal Component Analysis (PCA) and t-SNE.

• Linear, polynomial, and radial basis function (RBF).

How are new data points classified using an SVM model?

• By calculating the average distance to all data points in the training set.

• By mapping them to the same high-dimensional space and classifying using the decision boundary.

• By comparing them to the support vectors only.

• By calculating the probability of belonging to each class.

What is a common application of SVMs?

• Predicting continuous values.

• Time series forecasting.

• Image recognition and object detection.

• Sentiment analysis of text.

Which of the following is NOT a valid statement about SVMs?

• SVMs can be used for both classification and regression tasks.

• SVMs are sensitive to outliers in the data.

• SVMs always find a perfect separation between classes.

• SVMs aim to maximize the margin between the hyperplane and the closest data points.