3.5 Unsupervised Learning

Dependencies

Refer to the following markdown file for the respective sections of the class:

• Self Studies
• Lesson
• Assignment
• Quiz
• Reference

Lesson Objectives

Learners will understand:

• What are outliers and anomalies and how to detect them
• Dimensionality reduction techniques
• Clustering techniques

Learners will be able to:

• Detect outliers and anomalies
• Perform dimensionality reduction to reduce the number of features
• Perform clustering to group similar data points together

Lesson Plan

Duration	What	How or Why
- 5mins	Start zoom session	So that learners can join early and start class on time.
20 mins	Activity	Recap on self-study and prework materials.
40 mins	Code-along	Part 1: Outlier and Anomaly Detection.
	1 HR MARK
30 mins	Code-along	Part 2: Dimensionality Reduction.
10 mins	Break
20 mins	Code-along	Part 3: Clustering- K-Means.
	2 HR MARK
50 mins	Code-along	Part 4: Clustering- Hierarchical Clustering and DBSCAN.
10 mins	Briefing / Q&A	Brief on references, assignment, quiz and Q&A.
	END CLASS 3 HR MARK