Stronger convergence results for deep residual networks: network width scales linearly with training data size

DOI10.1093/IMAIAI/IAAA030OpenAlexW3108510223MaRDI QIDQ5095259FDOQ5095259

Authors: T. C. Gülcü 

Publication date: 5 August 2022

Published in: Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1911.04351

zbMATH Keywords

activation functionneural tangent kerneldeep network optimizationdeep residual networks

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cited In (2)

• Continuous limits of residual neural networks in case of large input data
• Globally Convergent Multilevel Training of Deep Residual Networks

This page was built for publication: Stronger convergence results for deep residual networks: network width scales linearly with training data size

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5095259)