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

DOI10.1007/978-3-031-38299-4_65arXiv2309.00699OpenAlexW4385434416MaRDI QIDQ6179069

Ferdinando Zanchetta, Francesco Faglioni, Rita Fioresi, M. Lapenna

Publication date: 16 January 2024

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2309.00699

zbMATH Keywords

statistical mechanicsmachine learninggeometric deep learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Graph theory (including graph drawing) in computer science (68R10) Equilibrium statistical mechanics (82B99)

Cites Work

• Unnamed Item
• The Fokker-Planck equation. Methods of solutions and applications.
• On the thermodynamic interpretation of deep learning systems
• An Efficient Learning Procedure for Deep Boltzmann Machines
• Information Theory and Statistical Mechanics
• Contact geometry for simple thermodynamical systems with friction
• Neurons with graded response have collective computational properties like those of two-state neurons.
• Entropy-SGD: biasing gradient descent into wide valleys

This page was built for publication: Geometric deep learning: a temperature based analysis of graph neural networks