Confusion-driven machine learning of structural phases of a flexible, magnetic Stockmayer polymer

Abstract

We use a semi-supervised, neural-network based machine learning technique, the confusion method, to investigate structural transitions in magnetic polymers, which we model as chains of magnetic colloidal nanoparticles characterized by dipole-dipole and Lennard-Jones interactions. As input for the neural network we use the particle positions and magnetic dipole moments of equilibrium polymer configurations, which we generate via replica-exchange Wang--Landau simulations. We demonstrate that by measuring the classification accuracy of neural networks, we can effectively identify transition points between multiple structural phases without any prior knowledge of their existence or location. We corroborate our findings by investigating relevant, conventional order parameters. Our study furthermore examines previously unexplored low-temperature regions of the phase diagram, where we find new structural transitions between highly ordered helicoidal polymer configurations.

References in corpus (42)

• An efficient, multiple range random walk algorithm to calculate the density of states
• Machine learning phases of matter
• Determining the density of states for classical statistical models: A random walk algorithm to produce a flat histogram
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Machine learning quantum phases of matter beyond the fermion sign problem
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• Machine Learning Phases of Strongly Correlated Fermions
• Deep Potentials for Materials Science
• Machine learning vortices at the Kosterlitz-Thouless transition
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Probing many-body localization with neural networks
• Kernel methods for interpretable machine learning of order parameters
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• A generic, hierarchical framework for massively parallel Wang-Landau sampling
• Microcanonical Analyses of Peptide Aggregation Processes
• Microcanonical entropy inflection points: Key to systematic understanding of transitions in finite systems
• Machine Learning for Condensed Matter Physics
• Scalable replica-exchange framework for Wang-Landau sampling
• Identifying polymer states by machine learning
• Shape anisotropy of polymers in disordered environment
• Applications of neural networks to the studies of phase transitions of two-dimensional Potts models
• Principal Component Analysis for Fermionic Critical Points
• Dynamics and polarization of superparamagnetic chiral nanomotors in a rotating magnetic field
• Machine learning dynamical phase transitions in complex networks
• Soft Metamaterials: Adaptation and Intelligence
• Effects of the dipolar interaction on the equilibrium morphologies of a single supramolecular magnetic filament in bulk
• Phase diagram for a single flexible Stockmayer polymer at zero field
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• Conformational phase diagram for polymers adsorbed at ultrathin nanowires
• A new paradigm for petascale Monte Carlo simulation: Replica exchange Wang-Landau sampling
• Machine learning of phase transitions in nonlinear polariton lattices
• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• Why neural functionals suit statistical mechanics
• Protein folding, anisotropic collapse and blue phases
• Kinetically driven helix formation during the homopolymer collapse process
• Learning entanglement breakdown as a phase transition by confusion
• Supervised and Unsupervised Machine Learning of Structural Phases of Polymers Adsorbed to Nanowires