On Breiman's dilemma in neural networks: phase transitions of margin dynamics

DOI10.4310/AMSA.2022.V7.N2.A4MaRDI QIDQ2084731zbMATH OpenOpenAlexFDO

Authors Weizhi Zhu, Yifei Huang, Yuan Yao

Publication date 13 October 2022

Published in Annals of Mathematical Sciences and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.4310/amsa.2022.v7.n2.a4

zbMATH Keywords

Breiman's dilemmaconvolutional neural networksmarginphase transitionRademacher complexity

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Phase transitions and learning in neural networks
• Boundary conditions and phase transitions in neural networks. Theoretical results
• Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise
• Threshold-induced phase transitions in perceptrons
• Boundary conditions and phase transitions in neural networks. Simulation results
• Phase transitions in the generalization behaviour of multilayer neural networks
• Weight-decay induced phase transitions in multilayer neural networks
• scientific article; zbMATH DE number 14855
• Theoretical analysis of learning dynamics near the opposite singularities in multilayer perceptrons
• Structural phase transitions in neural networks

This page was built for publication: On Breiman's dilemma in neural networks: phase transitions of margin dynamics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2084731)