Unformatted text preview: during their frequent
expeditions to explore strange new worlds, battle evil monsters, and attempt to rescue some princesses. Part A: Nearest Neighbors (20 Points)
You decide to use Nearest Neighbors to classify new creatures that Mario might encounter, based on
their positions on a map. In the map, friendly creatures are marked with a square, and enemies are
marked with monster icons.
A1 (12 points): On the following graph, draw the decision boundaries produced by 1-nearestneighbors. 17 A2 (8 points): The graph below shows two new creatures, marked with a question mark symbolsand
labeled A and B. Show how these will be classified using 3-nearest-neighbors and 5-nearest-neighbors
below. Creature A
Using 3 NN:
Using 5 NN: 18 Creature B Part B: ID-Trees (30 Points)
It turns out that enemies move around the world, so a simple K-Nearest-Neighbors on their location
won't do a very good job of protecting Mario. Instead, you decide to use an Identification Tree, based
on some characteristics of the creatures in this world, to classify creatures as Enemies (E...
View Full Document
This document was uploaded on 03/17/2014 for the course EECS 6.034 at MIT.
- Fall '10
- Artificial Intelligence