Resolution and relevance trade-offs in deep learning

DOI10.1088/1742-5468/aaf10fzbMath1456.68177arXiv1710.11324OpenAlexW2795932954MaRDI QIDQ3303274

Junghyo Jo, Juyong Song, Matteo Marsili

Publication date: 11 August 2020

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1710.11324

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (7)

A new spin on color quantization ⋮ Minimal model of permutation symmetry in unsupervised learning ⋮ A random energy approach to deep learning ⋮ The peculiar statistical mechanics of optimal learning machines ⋮ Statistical criticality arises in most informative representations ⋮ Multiscale relevance and informative encoding in neuronal spike trains ⋮ Maximal relevance and optimal learning machines

Uses Software

• darch
• PRMLT

Cites Work

• Unnamed Item
• Statistical mechanics of the US supreme court
• Are biological systems poised at criticality?
• Why does deep and cheap learning work so well?
• Reducing the Dimensionality of Data with Neural Networks
• On sampling and modeling complex systems
• Criticality of mostly informative samples: a Bayesian model selection approach
• Learning Deep Architectures for AI
• Least effort and the origins of scaling in human language
• A Fast Learning Algorithm for Deep Belief Nets

This page was built for publication: Resolution and relevance trade-offs in deep learning