Singular Value Decomposition and Neural Networks
arXiv:1906.11755 · doi:10.1007/978-3-030-30484-3_13
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.