Dimensionality reduction

Dimensionality reduction is one of the main applications of unsupervised learning . It can be understood as the process of reducing the number of random variables under consideration by getting a set of principal variables. High dimensionality has many costs, including redundant and irrelevant features which degrade the performance of some algorithms, difficulty in interpretation and visualization, and infeasible computation.

Categories

Dimensionality reduction can be devided into two subcategories:

• Feature selection:
  • Wrappers
  • Filters
  • Embedded
• Feature extraction:
  • Principal component analysis

Algorithms

Some of the most common dimensionality reduction algorithms in machine learning are listed as follows:

• Principal Component Analysis
• Kernel principal component analysis (Kernel PCA)
• Locally-Linear Embedding

• [1]
• [2]
• [3]