English

Asymptotic properties of one-layer artificial neural networks with sparse connectivity

Disordered Systems and Neural Networks 2021-12-13 v2 Probability Machine Learning

Abstract

A law of large numbers for the empirical distribution of parameters of a one-layer artificial neural networks with sparse connectivity is derived for a simultaneously increasing number of both, neurons and training iterations of the stochastic gradient descent.

Keywords

Cite

@article{arxiv.2112.00732,
  title  = {Asymptotic properties of one-layer artificial neural networks with sparse connectivity},
  author = {Christian Hirsch and Matthias Neumann and Volker Schmidt},
  journal= {arXiv preprint arXiv:2112.00732},
  year   = {2021}
}

Comments

12 pages, 4 figures