A note about why deep learning is deep: a discontinuous approximation perspective

DOI10.1002/STA4.654MaRDI QIDQ6548928

Yongxin Li, Haobo Qi, Hansheng Wang

Publication date: 3 June 2024

Published in: Stat (Search for Journal in Brave)

zbMATH Keywords

single-hidden-layer neural networksmulti-hidden-layer neural networks

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Multilayer feedforward networks are universal approximators
• Approximation by superpositions of a sigmoidal function
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)

This page was built for publication: A note about why deep learning is deep: a discontinuous approximation perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6548928)