[TBD]Role of Singular Value Decomposition in machine learning

Introduction

Laymen explanation

Singular Value Decomposition (SVD) is a widely used technique to decompose a matrix into several component matrices, exposing many of the useful and interesting properties of the original matrix.

If you love to know about this mathematical entity, then this document is for you.

Technical explanation

Matrix decomposition, also known as matrix factorization, involves describing a given matrix using its constituent elements.

Mathematical representation

Use in machine learning

• • SVD is used for dimensionality reduction in PCA

  • SVD is used for calculating pseudo inverse for rectangular matrics. Note that Matrix inversion is not defined for matrices that are not square

Reference

https://machinelearningmastery.com/singular-value-decomposition-for-machine-learning/

https://www.sciencedirect.com/topics/engineering/singular-value-decomposition

https://images.app.goo.gl/2eJPLXk8arJgRj586

https://images.app.goo.gl/c1BEktGM4RqX25zF6