A random energy approach to deep learning

DOI10.1088/1742-5468/ac7794OpenAlexW4226096684MaRDI QIDQ5101077

Rongrong Xie, Matteo Marsili

Publication date: 2 September 2022

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

Full work available at URL: https://arxiv.org/abs/2112.09420

zbMATH Keywords

learning theorymachine learningdeep learningenergy landscapes

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Statistical mechanics of the US supreme court
• Are biological systems poised at criticality?
• Dynamical criticality: overview and open questions
• Random-energy model: An exactly solvable model of disordered systems
• On sampling and modeling complex systems
• Resolution and relevance trade-offs in deep learning
• Statistical criticality arises in most informative representations
• Information, Physics, and Computation
• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• Maximal relevance and optimal learning machines
• The peculiar statistical mechanics of optimal learning machines
• The criticality hypothesis: how local cortical networks might optimize information processing
• Determining computational complexity from characteristic ‘phase transitions’

This page was built for publication: A random energy approach to deep learning