In supervised learning," Those who are near Zhu are red and those who are near Mo are black"Is used to describe which of the following models?

Question

Options

• AK-Means
• BSVM
• CKNN
• DNeural Networks

• A
  4% (1)
• B
  8% (2)
• C
  80% (20)
• D
  8% (2)

Explanation

KNN (K-Nearest Neighbors) is correct because the proverb captures its core mechanic exactly: a data point is classified based on the labels of its closest neighbors in feature space - just as a person's character is shaped by those around them. If your nearest neighbors are "red," you become "red."

Why the distractors are wrong:

• A (K-Means) is unsupervised clustering - it groups unlabeled data by centroid proximity, not by neighbor labels, and the question specifies supervised learning.
• B (SVM) classifies by finding a maximum-margin hyperplane between classes, not by examining neighboring points at prediction time.
• D (Neural Networks) learn through weighted connections and backpropagation - classification emerges from learned weights, not from proximity to training examples.

Memory tip: The "K" in the proverb maps to the "K" in KNN - K neighbors determine your color/class. Any time you see a "birds of a feather" or "you are who you hang with" analogy in ML questions, think KNN.

No community discussion yet for this question.