LearnViz CompSci
Home / Learn / AI & Machine Learning / k-Means Clustering

Beginner Topic 12 of 51 AI & Machine Learning

k-Means Clustering

Partitioning data into k groups around centroids.

How it works

k-means partitions data into k clusters by iterating two steps: assign each point to the nearest centroid, then recompute each centroid as the mean of its assigned points, repeating until assignments stop changing. It minimizes the within-cluster sum of squared distances, converging to a local optimum that depends on initialization, which k-means++ improves. The number of clusters k must be chosen, using the elbow method or silhouette scores.

Step-by-step walkthrough

  1. Choose k starting centres.
  2. Assign each point to its nearest centre.
  3. Move each centre to the mean of its points.
  4. Repeat until assignments stop changing.
  5. Results depend on k and the starting points.

Where it is used

Customer segmentation, image color quantization, document grouping, vector quantization and generating initial centers for other algorithms use k-means. It is fast and scales to large datasets.

Common pitfall

It assumes roughly spherical clusters of similar size and is sensitive to outliers and feature scaling. Results vary between runs, so run several initializations. It cannot find non-convex shapes, where DBSCAN or spectral clustering do better. Clusters may not reflect real groups. Standardize data, validate with domain knowledge and examine cluster profiles.

Where it fits in the course

k-Means Clustering is topic 12 of 51 in AI & Machine Learning, rated Beginner. It follows k-Nearest Neighbors. The next topic is Overfitting and Underfitting.

Practice and explore

How to study this topic

  1. Read the explanation above and restate the definition in your own words.
  2. Open the interactive lesson and answer its mini quiz.
  3. Read the common pitfall, then write a short example that avoids it.
  4. Check your understanding in the AI & Machine Learning quiz, and revisit the topic if you miss a question.

Frequently asked questions

What is k-Means Clustering?
Partitioning data into k groups around centroids. It belongs to AI & Machine Learning and is a beginner-level topic.
Where do people use k-Means Clustering?
Customer segmentation, image color quantization, document grouping, vector quantization and generating initial centers for other algorithms use k-means.
What is the most common mistake with k-Means Clustering?
It assumes roughly spherical clusters of similar size and is sensitive to outliers and feature scaling.
What should I learn before this topic?
Start with k-Nearest Neighbors, the topic just before it in AI & Machine Learning.
How can I practice it?
Answer the mini quiz in the interactive lesson, then take the AI & Machine Learning quiz.
Is k-Means Clustering hard to learn?
It is a Beginner topic, so it works as an entry point. If the terms are new, read the explanation twice and try the visualizer before the quiz.
How long does it take to learn k-Means Clustering?
Most learners can read the explanation and finish the interactive lesson in under an hour. Fluency comes from applying the idea, so plan a few short practice sessions with the quiz.
Which topics are related to k-Means Clustering?
k-Nearest Neighbors, Overfitting and Underfitting, Decision Trees are closely connected. The full list is in the related topics section of this page.
What should I study after k-Means Clustering?
Continue with Overfitting and Underfitting, the next topic in AI & Machine Learning.

Related topics