Abstract:These lecture notes introduce some topics of classical statistical physics, particularly those that are relevant for neural networks and deep learning. Statistical physics is treated as a branch of probability theory or statistics, with the goal of making concepts such as phase transitions and the renormalization group accessible to readers without prior knowledge of physics. We introduce the Boltzmann-Gibbs distribution and the thermodynamic potentials on a finite configuration space, notably for Ising spins and spin-glass models on a lattice, and then define phase transitions as discontinuities that arise in the limit that the number of lattice points goes to infinity. We further introduce Hopfield networks and Boltzmann machines, which are governed by the same energy function as spin-glass models, and discuss the learning algorithm for restricted Boltzmann machines. In this algorithm hidden neurons are integrated out as in the renormalization group. Finally, modern deep learning is introduced, whose early developments were in part motivated by restricted Boltzmann machines in that they carry many layers of hidden neurons. A description of large language models is given.
| Comments: | 56 pages, 7 figures, based on a course given at Humboldt University Berlin |
| Subjects: | Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (cs.LG); High Energy Physics - Theory (hep-th) |
| Cite as: | arXiv:2605.06394 [cond-mat.dis-nn] |
| (or arXiv:2605.06394v1 [cond-mat.dis-nn] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06394 arXiv-issued DOI via DataCite |
From: Olaf Hohm [view email]
[v1]
Thu, 7 May 2026 15:08:49 UTC (710 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。