Empirical evidence for ultrametric structure in multi-layer perceptron error surfaces

DOI10.1023/A:1019956303894zbMATH Open1008.68764MaRDI QIDQ1857773FDOQ1857773

Authors: Yanyan Li 

Publication date: 19 February 2003

Published in: Neural Processing Letters (Search for Journal in Brave)

Recommendations

• Learning in ultrametric committee machines
• A method that reveals the multi-level ultrametric tree hidden in p-spin-glass-like systems
• A numerical study of ultrametricity in finite-dimensional spin glasses
• Ultrametricity in mean-field spin glasses
• A quantitative clustering approach to ultrametricity in spin glasses

zbMATH Keywords

ultrametricityfeedforward neural networkmulti-layer perceptronerror surfaceconfiguration space analysis

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies and applications (68U99)

This page was built for publication: Empirical evidence for ultrametric structure in multi-layer perceptron error surfaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1857773)