Explore the fundamentals of the k-nearest neighbors algorithm in this 26-minute video lecture from the End to End Machine Learning School. Discover how k-NN works for both classification and regression tasks, understand the importance of choosing the right k value, and learn about feature scaling and distance metrics. Delve into the application of k-NN with categorical data and examine its limitations, including computational expense with large datasets and sensitivity to feature scaling and distance metrics.
Overview
Syllabus
Intro
for classification
Choice of k matters
Feature scaling matters
Distance metric matters
K-NN with categorical data
for regression
Expensive to compute with large data sets. Sensitive to feature scaling. Sensitive to distance metric.
Taught by
Brandon Rohrer
