Unsupervised Learning

It helps us solve problems where we have little or no idea what the output should looked like i.e our data is unlabelled. We try to derive a structure or relationship from data by clustering it based on relationships of variables in the data. As we don’t know what the results should be like there is no feedback on the predictions.

Get Sayak Chattopadhyay’s stories in your inbox

Join Medium for free to get updates from this writer.

Remember me for faster sign in

There are various types of clustering algorithms:

• Hierarchical clustering
• K-means clustering
• K-NN (k nearest neighbors)
• Principal Component Analysis
• Singular Value Decomposition
• Independent Component Analysis

More details on each of these in subsequent articles