# Clustering

Everyone
• 13 videos | 1h 11m 9s
• Includes Assessment
Rating 4.0 of 1 users (1)
How do we get from raw data to improving the level of performance? The answer is found in this opening course, which introduces us to the tools and techniques developed to make sense of unstructured data and discover hidden patterns.

## WHAT YOU WILL LEARN

• Describe what unsupervised learning is and why is it challenging
Identify unsupervised learning problems
Describe what clustering is
Identify when to use clustering
Understand the set up for the k-means algorithm
Define the k-means clustering problem and understand the k-means algorithm as a way to solve it
Evaluate the output of the k-means algorithm
• Understand what happens when we don't get a desired result from the k-means algorithm
Understand what may cause someone to go beyond k-means clustering
Describe different notions of similarity and clustering
Know how to prepare data so that the k-means algorithm will produce the best results
Understand how the number of clusters in data may not always be finite
Know that clustering is not always the right answer for finding the patterns in data

## IN THIS COURSE

• Start off the course by learning what unsupervised learning is and understand what its challenges are.
• Now you know what unsupervised learning is, let's learn how to identify these types of problems.
• 3.  What Is Clustering?
There are a lot of different problems that can be solved with unsupervised learning. Now learn about the most popular problem, clustering.
• 4.  When To Use Clustering
In the last video you learned that clustering is a particular form of unsupervised learning. Now go through more examples of clustering and see why and when you might want to use it in practice
• 5.  K-Means Preliminaries
Now that you have learned about clustering, learn about the most popular algorithm for clustering.
• 6.  The K-Means Algorithm
In the last video, we set up the k-means clustering problem as a particular subset of general clustering problems. Now develop the k-means algorithm.
• 7.  How To Evaluate Clustering
The last couple of videos have set up the k-means algorithm. Learn how to evaluate the output of this algorithm.
• 8.  Beyond K-Means: What Really Makes A Cluster?
Now that you understand the algorithm, what happens if the output is unexpected or unwanted? Learn how to troubleshoot the k-means algorithm.
• 9.  Beyond K-Means: Other Notions Of Distance
Explore the notion of what makes a cluster and what motivates us to look at clustering problems and models beyond K-Means clustering.
• 10.  Beyond K-Means: Grouping Data By Similarity
Learn about different notions of similarity and clustering other than the squared Euclidean distance required.
• 11.  Beyond K-Means: Data And Pre-Processing
Take a closer look at data and how to prepare it for the k-means algorithm.
• 12.  Beyond K-Means: Big Data and Nonparametric Bayes
You have learned a lot about a fixed number of clusters. Learn about why that may not always be the case.
• 13.  Beyond Clustering
All of the videos before have talked about clustering. Now learn why that may not always be the best method.

## YOU MIGHT ALSO LIKE

Channel Green Belt
Rating 5.0 of 3 users (3)
Rating 5.0 of 1 users (1)