Aarhus University Seal

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

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Christian Hirsch
  • Matthias Neumann, Ulm University
  • ,
  • Volker Schmidt, Ulm University

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

Original languageEnglish
Article number109698
JournalStatistics & Probability Letters
Publication statusPublished - Feb 2023

Bibliographical note

Publisher Copyright:
© 2022 Elsevier B.V.

    Research areas

  • Artificial neural network, Law of large numbers, Random network, Sparse connectivity, Stochastic gradient descent, Weak convergence

See relations at Aarhus University Citationformats

ID: 312883567