An introduction to machine learning: a perspective from statistical physics
From MaRDI portal
Publication:6140146
DOI10.1016/J.PHYSA.2022.128154arXiv2202.05670MaRDI QIDQ6140146FDOQ6140146
Authors: Aurélien Decelle 
Publication date: 19 January 2024
Published in: Physica A (Search for Journal in Brave)
Abstract: The recent progresses in Machine Learning opened the door to actual applications of learning algorithms but also to new research directions both in the field of Machine Learning directly and, at the edges with other disciplines. The case that interests us is the interface with physics, and more specifically Statistical Physics. In this short lecture, I will try to present first a brief introduction to Machine Learning from the angle of neural networks. After explaining quickly some fundamental models and global aspects of the training procedure, I will discuss into more detail two examples illustrate what can be done from the Statistical Physics perspective.
Full work available at URL: https://arxiv.org/abs/2202.05670
Cites Work
- Pattern recognition and machine learning.
- Deep learning
- Neural networks and physical systems with emergent collective computational abilities
- Mean field models for spin glasses. Volume I: Basic examples.
- Training Products of Experts by Minimizing Contrastive Divergence
- On the equivalence of Hopfield networks and Boltzmann machines
- Information, Physics, and Computation
- Title not available (Why is that?)
- Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
- Statistical Physics of Spin Glasses and Information Processing
- Statistical mechanics of learning
- Quiet planting in the locked constraint satisfaction problems
- The Nishimori line and Bayesian statistics
- Generalized Guerra's interpolation schemes for dense associative neural networks
- Thermodynamics of restricted Boltzmann machines and related learning dynamics
- An Introduction to Variational Autoencoders
- Comparing dynamics: deep neural networks versus glassy systems
- Optimal errors and phase transitions in high-dimensional generalized linear models
- Gaussian-spherical restricted Boltzmann machines
- Machine learning and statistical physics: preface
- Learning curves of generic features maps for realistic datasets with a teacher-student model*
- Equilibrium and non-equilibrium regimes in the learning of restricted Boltzmann machines*
- ‘Place-cell’ emergence and learning of invariant data with restricted Boltzmann machines: breaking and dynamical restoration of continuous symmetries in the weight space
This page was built for publication: An introduction to machine learning: a perspective from statistical physics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6140146)
