English

Singular Value Decomposition and Neural Networks

Machine Learning 2019-09-16 v1 Numerical Analysis Numerical Analysis Machine Learning

Abstract

Singular Value Decomposition (SVD) constitutes a bridge between the linear algebra concepts and multi-layer neural networks---it is their linear analogy. Besides of this insight, it can be used as a good initial guess for the network parameters, leading to substantially better optimization results.

Cite

@article{arxiv.1906.11755,
  title  = {Singular Value Decomposition and Neural Networks},
  author = {Bernhard Bermeitinger and Tomas Hrycej and Siegfried Handschuh},
  journal= {arXiv preprint arXiv:1906.11755},
  year   = {2019}
}
R2 v1 2026-06-23T10:05:38.883Z