Influence of anisotropy on the study of critical behavior of spin models by machine learning methods

Abstract

In this paper, we applied a deep neural network to study the issue of knowledge transferability between statistical mechanics models. The following computer experiment was conducted. A convolutional neural network was trained to solve the problem of binary classification of snapshots of the Ising model's spin configuration on a two-dimensional lattice. During testing, snapshots of the Ising model spins on a lattice with diagonal ferromagnetic and antiferromagnetic connections were fed to the input of the neural network. Estimates of the probability of samples belonging to the paramagnetic phase were obtained from the outputs of the tested network. The analysis of these probabilities allowed us to estimate the critical temperature and the critical correlation length exponent. It turned out that at weak anisotropy the neural network satisfactorily predicts the transition point and the value of the correlation length exponent. Strong anisotropy leads to a noticeable deviation of the predicted values from the precisely known ones. Qualitatively, strong anisotropy is associated with the presence of oscillations of the correlation function above the Stephenson disorder temperature and further approach to the point of the fully frustrated case.

arXiv comment5 pages, 5 figures

References in corpus (9)

• Machine learning and the physical sciences
• Machine learning phases of matter
• Critical Binder cumulant in two-dimensional anisotropic Ising models
• Nonuniversal finite-size scaling in anisotropic systems
• The critical Binder cumulant in a two--dimensional anisotropic Ising model with competing interaction
• Topological aspects of symmetry breaking in triangular-lattice Ising antiferromagnets
• Nature of phase transition(s) in striped phase of triangular-lattice Ising antiferromagnet
• Finite-size analysis in neural network classification of critical phenomena
• Exact Critical Casimir Amplitude of Anisotropic Systems from Conformal Field Theory and Self-Similarity of Finite-Size Scaling Functions in $d\ge 2$ Dimensions

Cited by in corpus (2)

• Machine Learning Domain Adaptation in Spin Models with Continuous Phase Transitions
• Phase probabilities in first-order transitions using machine learning