Support Vector Machines and k-NN Quiz

What is the primary objective of Support Vector Machines (SVM)?

• To maximize the margin between classes

• To minimize the number of support vectors

• To reduce training time

• To maximize the number of misclassified points

In SVM, what is a Support Vector?

• A data point closest to the decision boundary

• A point farthest from the hyperplane

• A randomly chosen data point

• A data point with the highest weight

Which kernel function is commonly used in SVM for handling non-linearly separable data?

• Linear Kernel

• Polynomial Kernel

• Radial Basis Function (RBF) Kernel

• Sigmoid Kernel

k-Nearest Neighbors (k-NN) is a type of:

• Supervised Learning Algorithm

• Unsupervised Learning Algorithm

• Reinforcement Learning Algorithm

• Semi-Supervised Learning Algorithm

How does k-NN classify a new data point?

• By computing the mean of all data points

• By finding the k closest training examples and taking a majority vote

• By using a decision tree to find the class

• By selecting a random class

In SVM, what is the purpose of the kernel trick?

• To increase the number of dimensions

• To transform data into higher-dimensional space for better separation

• To make SVM faster

• To remove noise from the dataset

What happens when a very small value of 'k' is used in k-NN?

• The model generalizes well

• The model becomes less sensitive to noise

• The model may overfit the training data

• The model underfits the data

In k-NN, what distance metric is most commonly used?

• Cosine Similarity

• Manhattan Distance

• Euclidean Distance

• Jaccard Similarity

Which of the following is a drawback of k-NN?

• It requires labeled training data

• It has a high training time complexity

• It is sensitive to the choice of k and distance metric

• It cannot be used for classification problems

What is the time complexity of classifying a new instance in k-NN?

• O(1)

• O(log n)

• O(n)

• O(n²)