#choice-of-k

1 question from Nearest Neighbors & Kernel Methods

Timed test

1 question · 1 min · score and explanations at the end

Q 1 / 1Score 0 / 0

Shuffle questions

Question 1: Single choice

easyAI-checkedNearest Neighbors & Kernel Methods

A kNN classifier with plain majority voting is trained on $N$ labeled points. What happens if you set $k = N$ ?

The decision boundary becomes the Voronoi diagram of the training points1
The prediction becomes undefined because of ties2
Every query gets the majority class of the training set3
The classifier memorizes the training set exactly, as with $k = 1$ 4

Keys: 1–9 select · Enter check / next