00:01
So here is the question, in k nearest neighbors which is known as k and n classification, the decision boundary is determined by the k nearest data point from each class.
00:23
So let's consider like part a decision boundary for k drawn by will be drawn by connecting each data point to its, this means that decision boundary will pass between the nearest neighbor points trying to separate two classes as best as it can be the nearest neighbor.
00:57
Second when k equals to 3, so the decision boundary for this will be drawn by considering three nearest neighbor, three nearest neighbors for each data point for each data point.
01:21
This result in a smoother decision boundaries that take into account more neighbor to classifier point.
01:27
Now for the b part, classification of point of points 8 6 and 8 4.
01:40
So first for k equals to 1, here point 8 6 will be classified based on the, based on nearest neighbor which is a blue square, which is a blue square.
01:57
Therefore it is classified as the blue square...