Clustering and it's Types in Machine Learning

This presentation describes about Clustering and it's types in Machine Learning

1. Clustering and Its Types

2. Introduction to Clustering • Clustering is a technique used to group similar data points together. • It is an unsupervised learning technique used in data mining and machine learning. • The goal is to discover inherent patterns in data.

3. Types of Clustering 1. Hard Clustering: Each data point belongs to only one cluster. In this type of clustering, each data point belongs to a cluster completely or not. For example, Let’s say there are 4 data point and we have to cluster them into 2 clusters. So each data point will either belong to cluster 1 or cluster 2.

4. Data Points Clusters A C1 B C2 C C2 D C1

5. 2. Soft Clustering: A data point can belong to multiple clusters with probabilities. In this type of clustering, instead of assigning each data point into a separate cluster, a probability or likelihood of that point being that cluster is evaluated. For example, Let’s say there are 4 data point and we have to cluster them into 2 clusters. So we will be evaluating a probability of a data point belonging to both clusters. This probability is calculated for all data points.

6. Data Points Probability of C1 Probability of C2 A 0.91 0.09 B 0.3 0.7 C 0.17 0.83 D 1

7. Uses of Clustering • Customer segmentation in marketing • Anomaly detection in security • Medical image segmentation • Document classification and topic modeling • Social network analysis

8. Clustering Methods Clustering is the process of determining how related the objects are grouped  based on a metric called the similarity measure . Various types of clustering algorithms are: Centroid-based Clustering( Partitioningmethods ) Density-based Clustering (Model-based methods) Connectivity- basedClustering ( Hierarchicalclustering )

9.  Centroid-based Clustering (Partitioning methods) Centroid-based clustering organizes data points around central vectors (centroids) that represent clusters. Each data point belongs to the cluster with the nearest centroid. Generally, the similarity measure chosen for these algorithms are Euclidian distance. K-means and K-medoids clustering

10. Density-Based Clustering (Model-Based Methods) Density-based clustering groups data points based on regions of high density separated by low-density areas . Unlike centroid-based clustering, it does not require specifying the number of clusters beforehand. Instead, it identifies clusters by detecting dense regions in the dataset . These methods are useful for irregularly shaped clusters and datasets with noise or outliers .

11. Connectivity-based Clustering (Hierarchical clustering) Connectivity-based clustering , also known as Hierarchical Clustering , builds clusters step-by-step based on the similarity or distance between data points. Unlike centroid-based clustering, hierarchical clustering does not require specifying the number of clusters (k) in advance .

12. Distribution-based Clustering Distribution-based clustering is a technique that assumes  data points are generated from a mixture of probability distributions (e.g., Gaussian, Poisson, etc.) . The goal is to identify clusters by estimating the parameters of these distributions. In distribution-based clustering:

13. Fuzzy Clustering Fuzzy clustering allows data points to belong to multiple clusters with varying degrees of membership.  Each data point is assigned a membership value between 0 and 1 for every cluster. These membership values indicate the degree to which a data point belongs to a particular cluster.

14. Applications of Clustering • Image processing and pattern recognition • Fraud detection in banking • Recommender systems • Genomic data analysis • Climate data analysis