Clustering in Machine Learning - Soft Clustering

Welcome back readers!! In the previous article, we discussed various hard clustering techniques. In this article, we will discuss soft clustering techniques. They are categorized as Fuzzy c-Means and Gaussian Mixture Model.

Fuzzy c-Means

The concept of fuzzy logic comes into play when the probability of occurrence of an event can be any value between 0 and 1. So, there are possibilities that a data value can belong to more than one cluster. The algorithm is designed similar to k-Means clustering, but centres are estimated using fuzzy logic. Key points are as follows:

• Used when number of clusters is known.
• Used for pattern recognition.
• Used when clusters overlap.

Gaussian Mixture Model

When there are different multivariate Gaussian or Normal distributions of data points, each distribution with a certain probability, Gaussian Mixture Model is used. Key points are as follows:

• Used when the data point belongs to more than one cluster.
• Used when clusters have different sizes and correlation structures within them.

Reference: Machine Learning with MATLAB (eBook)

Hope you people like this article. Please give your feedback on this article of Deep Learning Series and suggestions for future articles in the comment section below 👇.