Practice Library
All MCQs
Browse exam-wise, subject-wise, and country-wise MCQs with explanations.
Choose an option to check your answer.
Correct Answer: A. Low, because it mainly stores the training data
Explanation:
KNN has little parameter fitting.
Its main computational burden occurs during prediction.
Choose an option to check your answer.
Correct Answer: D. Distances become less discriminative as dimensions increase
Explanation:
High-dimensional space is sparse and nearest points may still be far away.
Irrelevant features further obscure meaningful neighborhoods.
Choose an option to check your answer.
Correct Answer: C. Jaccard similarity
Explanation:
Jaccard focuses on shared presences and ignores shared absences.
This suits applications such as document-term or purchase data.
Choose an option to check your answer.
Correct Answer: B. When coordinate-wise absolute differences are more appropriate or outlier sensitivity should be reduced
Explanation:
Manhattan distance sums absolute differences rather than squared contributions.
It can be more robust in some high-dimensional settings.
Choose an option to check your answer.
Correct Answer: A. Euclidean distance
Explanation:
Euclidean distance measures straight-line separation in feature space.
Standardization is important because it is scale-sensitive.
Choose an option to check your answer.
Correct Answer: D. Gives closer neighbors greater influence than farther neighbors
Explanation:
Distance weighting recognizes that nearby examples may be more relevant.
A common rule uses inverse distance weights.
Choose an option to check your answer.
Correct Answer: C. It reduces the chance of a tied vote
Explanation:
An odd number of neighbors cannot split evenly between two classes.
Ties can still arise through weighted voting or distance equality.
Choose an option to check your answer.
Correct Answer: B. By comparing validation or cross-validation performance
Explanation:
K is a hyperparameter controlling local smoothness.
Validation estimates which value generalizes best.
Choose an option to check your answer.
Correct Answer: A. High bias and dominance by broad class prevalence
Explanation:
Large neighborhoods smooth local structure and may underfit.
The majority class can overwhelm minority patterns.
Choose an option to check your answer.
Correct Answer: D. Low bias but high variance
Explanation:
Small neighborhoods closely follow local training detail.
This flexibility can overfit noise.
Choose an option to check your answer.
Correct Answer: C. The class of the single nearest training point is predicted
Explanation:
One-nearest neighbor creates highly flexible local boundaries.
It can be sensitive to noise and mislabeled examples.
Choose an option to check your answer.
Correct Answer: B. It postpones most computation until prediction time
Explanation:
KNN does not fit an explicit global model during training.
It retains examples and searches neighbors for each new case.
