SciPost Physics Core

SciPost Phys. Core 5, 032 (2022) · published 8 June 2022

• doi: 10.21468/SciPostPhysCore.5.2.032
• pdf
• BiBTeX
• RIS
• Submissions/Reports
• 

Abstract

The applicability of artificial neural networks (ANNs) is typically limited to the models they are trained with and little is known about their generalizability, which is a pressing issue in the practical application of trained ANNs to unseen problems. Here, by using the task of identifying phase transitions in spin models, we establish a systematic generalizability such that simple ANNs trained with the two-dimensional ferromagnetic Ising model can be applied to the ferromagnetic q-state Potts model in different dimensions for q>=2. The same scheme can be applied to the highly nontrivial antiferromagnetic q-state Potts model. We demonstrate that similar results can be obtained by reducing the exponentially large state space spanned by the training data to one that comprises only three representative configurations artificially constructed through symmetry considerations. We expect our findings to simplify and accelerate the development of machine learning-assisted tasks in spin-model related disciplines in physics and materials science.

• Chen et al., Study of phase transition of Potts model with Domain Adversarial Neural Network
  Physica A: Statistical Mechanics and its Applications 617, 128666 128666 (2023) [Crossref]
• Wang et al., Supervised and unsupervised learning of (1+1) -dimensional even-offspring branching annihilating random walks
  Mach. Learn.: Sci. Technol. 5, 015033 (2024) [Crossref]
• Chen et al., Applications of Domain Adversarial Neural Network in phase transition of 3D Potts model
  Physica A: Statistical Mechanics and its Applications 637, 129533 129533 (2024) [Crossref]
• Tseng et al., Learning the phase transitions of two-dimensional Potts model with a pre-trained one-dimensional neural network
  Results in Physics 56, 107264 107264 (2024) [Crossref]
• Peng et al., Phase transitions of the four-state Potts model on the square and honeycomb lattices
  2024, 013A04 (2024) [Crossref]