ABSTRACT
Clustering techniques are widely used to identify groups or clusters that exhibit similarity within their data. These are used for exploratory data analysis and in various application areas. One such clustering method is Spectral Embedding. In this chapter, we will discuss in detail this clustering technique and how it is closely related to another dimensionality reduction technique called Laplacian Eigenmap. This chapter starts with a detailed explanation of spectral clustering and how it is used for clustering data. Further, the advantages and shortcomings of this clustering algorithm are also discussed. Finally, the chapter ends with examples using datasets along with a tutorial to demonstrate how data is clustered using spectral clustering.
