On the thermodynamic interpretation of deep learning systems

DOI10.1007/978-3-030-80209-7_97OpenAlexW3180071016MaRDI QIDQ2117965FDOQ2117965

Authors: Rita Fioresi, Francesco Faglioni, Francesco Morri, Lorenzo Squadrani 

Publication date: 22 March 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-80209-7_97

Recommendations

• Thermodynamics of restricted Boltzmann machines and related learning dynamics
• Nonequilibrium thermodynamics of self-supervised learning
• scientific article; zbMATH DE number 1096541
• Deep learning of thermodynamics-aware reduced-order models from data
• Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
• Statistical mechanics of training in neural networks
• scientific article; zbMATH DE number 1163210
• Statistical Mechanics of Neural Networks

zbMATH Keywords

deep learningstatistical mechanicsLie groups machine learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Classical thermodynamics, heat transfer (80-XX)

Cites Work

• Information Theory and Statistical Mechanics
• Neurons with graded response have collective computational properties like those of two-state neurons
• An efficient learning procedure for deep Boltzmann machines
• Contact geometry for simple thermodynamical systems with friction

Cited In (1)

• Geometric deep learning: a temperature based analysis of graph neural networks

Uses Software

• ImageNet
• AlexNet

This page was built for publication: On the thermodynamic interpretation of deep learning systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117965)