Parameter diagnostics of phases and phase transition learning by neural networks

Abstract

We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

arXiv comment14 pages, 23 figures

References in corpus (14)

• Machine learning phases of matter
• Learning phase transitions by confusion
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Machine Learning Topological Invariants with Neural Networks
• Machine learning vortices at the Kosterlitz-Thouless transition
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Kernel methods for interpretable machine learning of order parameters
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Deep Learning the Ising Model Near Criticality
• Quantum phase recognition via unsupervised machine learning
• Essential finite-size effect in the 2D XY model
• Towards meaningful physics from generative models

Cited by in corpus (48)

• Identifying topological order through unsupervised machine learning
• Machine Learning for Quantum Matter
• Machine learning of phase transitions in the percolation and XY models
• Machine Learning for Condensed Matter Physics
• Deep Learning Topological Invariants of Band Insulators
• Machine-Learning Studies on Spin Models
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• Learning multiple order parameters with interpretable machines
• Smallest Neural Network to Learn the Ising Criticality
• Supervised learning magnetic skyrmion phases
• Thermodynamics and Feature Extraction by Machine Learning
• Machine learning topological phases in real space
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Mapping distinct phase transitions to a neural network
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
• Topological Persistence Machine of Phase Transitions
• Machine-learning detection of the Berezinskii-Kosterlitz-Thouless transitions in the q-state clock models
• Extending machine learning classification capabilities with histogram reweighting
• Phase transition encoded in neural network
• Finite-size analysis in neural network classification of critical phenomena
• Neural Network flows of low q-state Potts and clock Models
• Continuous-mixture Autoregressive Networks for efficient variational calculation of many-body systems
• Mapping out phase diagrams with generative classifiers
• Machine-learning detection of the Berezinskii-Kosterlitz-Thouless transition and the second-order phase transition in the XXZ models
• Profile approach for recognition of three-dimensional magnetic structures
• Machine learning for percolation utilizing auxiliary Ising variables
• Learning Order Parameters from Videos of Dynamical Phases for Skyrmions with Neural Networks
• Deep learning of deformation-dependent conductance in thin films: nanobubbles in graphene
• Investigating Berezinskii-Kosterlitz-Thouless phase transitions in Kagome spin ice by quantifying Monte Carlo process: Distribution of Hamming distances
• Machine learning phase transitions of the three-dimensional Ising universality class
• Adversarial Machine Learning Phases of Matter
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Detecting composite orders in layered models via machine learning
• Phase determination with and without deep learning
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• Machine learning of phases and structures for model systems in physics
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• Probing phase transitions with correlations in configuration space
• Characterization of photoexcited states in the half-filled one-dimensional extended Hubbard model assisted by machine learning
• Machine Learning Percolation Model
• Berezinskii-Kosterlitz-Thouless transition from Neural Network Flows
• Fluctuation based interpretable analysis scheme for quantum many-body snapshots
• Machine-Learning Detection of the Berezinskii-Kosterlitz-Thouless Transitions
• Randomized-gauge test for machine learning of Ising model order parameter
• Autonomous Discovery of the Ising Model's Critical Parameters with Reinforcement Learning