Week 1: Unsupervised Learning

This week, you will learn two key unsupervised learning algorithms: clustering and anomaly detection

Learning Objectives

• Implement the k-means optimization objective

• Initialize the k-means algorithm

• Choose the number of clusters for the k-means algorithm

• Implement an anomaly detection system

• Decide when to use supervised learning vs. anomaly detection

• Implement the centroid update function in k-means

• Implement the function that finds the closest centroids to each point in k-means

Welcome to the course

Welcome! - Video • Duration: 3 min

[IMPORTANT] Have questions, issues or ideas? Join our Community! - Ungraded External Tool • Duration: 20 min

Clustering

What is clustering? - Video • Duration: 4 min

K-means intuition - Video • Duration: 6 min

K-means algorithm - Video • Duration: 9 min

Optimization objective - Video • Duration: 11 min

Initializing K-means - Video • Duration: 8 min

Choosing the number of clusters - Video • Duration: 7 min

Practice Quiz: Clustering

Clustering

Practice Lab 1

k-means

Anomaly detection

Finding unusual events - Video • Duration: 11 min

Gaussian (normal) distribution - Video • Duration: 10 min

Anomaly detection algorithm - Video • Duration: 12 min

Developing and evaluating an anomaly detection system - Video • Duration: 11 min

Anomaly detection vs. supervised learning - Video • Duration: 8 min

Choosing what features to use - Video • Duration: 14 min

Practice Quiz: Anomaly detection

Anomaly detection

Practice Lab 2

Anomaly Detection