Predicting long- and short-range order with restricted Boltzmann machine
Source abstract
Abstract
Generalization properties of the restricted Boltzmann machine (RBM) for two-dimensional Ising model are investigated. Both long-range and short-range order are examined: the first is studied for a spin lattice with ferromagnetic interaction, and the second is considered for a binary alloy on the square lattice. For each of these cases, algorithms are proposed that allow the once trained RBM to predict the order parameters for any temperature and alloy concentration.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Model Reduction and Neural Networks · Generative Adversarial Networks and Image Synthesis · Neural Networks and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Physical-Technical Institute, UdmFRC UB RAS , Izhevsk 426067, Russian Federation
Funding
Ministry of Science and Higher Education of the Russian Federation
References (27)
Show source-provided references
1. Deep learning10.1038/nature14539 ↗
2. Discovering phase transitions with unsupervised learning10.1103/physrevb.94.195105 ↗
3. Machine learning phases of matter10.1038/nphys4035 ↗
4. Machine learning phases of strongly correlated fermions10.1103/physrevx.7.031038 ↗
5. Self-learning Monte Carlo method10.1103/physrevb.95.041101 ↗
6. Accelerated Monte Carlo simulations with restricted Boltzmann machines10.1103/physrevb.95.035105 ↗
7. Self-learning Monte Carlo with deep neural networks10.1103/physrevb.97.205140 ↗
8. Ani-1: An extensible neural network potential with dft accuracy at force field computational cost10.1039/c6sc05720a ↗
9. Quantum entanglement in neural network states10.1103/physrevx.7.021021 ↗
10. Y. Levine, D. Yakira, N. Cohen, and A. Shashua, “Deep learning and quantum entanglement: Fundamental connections with implications to network design,” arXiv:1704.01552 [cs.LG] (2017).
11. Searching for exotic particles in high-energy physics with deep learning10.1038/ncomms5308 ↗
12. Deep learning in color: Towards automated quark/gluon jet discrimination10.1007/jhep01(2017)110 ↗
13. Machine learning and the physical sciences10.1103/revmodphys.91.045002 ↗
14. A high-bias, low-variance introduction to machine learning for physicists10.1016/j.physrep.2019.03.001 ↗
15. Information processing in dynamical systems: Foundations of harmony theory
16. Learning thermodynamics with Boltzmann machines10.1103/physrevb.94.165134 ↗
17. Deep learning the ising model near criticality
18. Solving the quantum many-body problem with artificial neural networks10.1126/science.aag2302 ↗
19. A learning algorithm for Boltzmann machines10.1207/s15516709cog0901_7 ↗
20. A practical guide to training restricted Boltzmann machines10.1007/978-3-642-35289-8 ↗
21. Crystal statistics. I. A two-dimensional model with an order-disorder transition10.1103/physrev.65.117 ↗
22. 1979
23. Allowance for the short-range atomic order in describing the magnetic properties of disordered metal-metalloid alloys10.1016/0304-8853(95)00499-8 ↗
24. An approximate theory of order in alloys10.1103/physrev.77.669 ↗
25. 1969
26. 1982
27. Training products of experts by minimizing contrastive divergence10.1162/089976602760128018 ↗