K Means
K Means Clustering
K Means
K Means Clustering
less than a minute
This course includes
6 articles
13 mins reading time
6 videos • 1 hr 33 mins
Course content
6 sections • 32 topics • Read: 13 mins • Video: 1 hr 33 mins
K Means
Unsupervised Learning
Real-World Motivations for Clustering
Key Insight
Problem Statement
Optimization Perspective
Optimization
Variance Decomposition
Combinatorial Explosion
K-Means Clustering | Variance Decomposition | Why NP Hard Problem ? | Explained with Example
Lloyds Algorithm
Idea
Lloyd's Algorithm
Issues
Solutions
Lloyd’s Algorithm | K Means | Explained with Example
K Means++
Issues with Random Initialization
K-Means++ Algorithm
Problem
Solution
K Means++ Algorithm | Issues with Random Initialization | Explained with Example
K Medoid
Issues with K-Means
Medoid
K-Medoids (PAM) Algorithm
Advantages
K-Medoids Algorithm | Partitioning Around Medoids (PAM) | Explained with Example
Clustering Quality Metrics
How to Evaluate Quality of Clustering?
Elbow Method
Dunn Index [0, \(\infty\))
Measure of Closeness
Clustering Quality Metrics | Elbow Method | Dunn Index | Explained with Example
Silhouette Score
How to Evaluate Quality of Clustering?
Silhouette Score [-1, 1]
Silhouette Score Formula
Cohesion a(i)
Separation b(i)
Silhouette Plot
Geometric Interpretation
Silhouette Score Vs Dunn Index
Silhouette Score | Dunn Index Vs Silhouette Score | Explained with Example
Lloyds Algorithm
Lloyds Algorithm
K Means++
K Means++ Algorithm
K Medoid
K Medoid
Clustering Quality Metrics
Clustering Quality Metrics
Silhouette Score
Silhouette Score