English

On the overfly algorithm in deep learning of neural networks

Machine Learning 2019-01-15 v6 Dynamical Systems Machine Learning

Abstract

In this paper we investigate the supervised backpropagation training of multilayer neural networks from a dynamical systems point of view. We discuss some links with the qualitative theory of differential equations and introduce the overfly algorithm to tackle the local minima problem. Our approach is based on the existence of first integrals of the generalised gradient system with build-in dissipation.

Keywords

Cite

@article{arxiv.1807.10668,
  title  = {On the overfly algorithm in deep learning of neural networks},
  author = {Alexei Tsygvintsev},
  journal= {arXiv preprint arXiv:1807.10668},
  year   = {2019}
}

Comments

To appear in Applied Mathematics and Computation

R2 v1 2026-06-23T03:17:10.531Z