Supervised and Unsupervised Machine Learning of Structural Phases of Polymers Adsorbed to Nanowires

Abstract

We identify configurational phases and structural transitions in a polymer nanotube composite by means of machine learning. We employ various unsupervised dimensionality reduction methods, conventional neural networks, as well as the confusion method, an unsupervised neural-network-based approach. We find neural networks are able to reliably recognize all configurational phases that have been found previously in experiment and simulation. Furthermore, we locate the boundaries between configurational phases in a way that removes human intuition or bias. This could be done before only by relying on preconceived, ad-hoc order parameters.

References in corpus (12)

• Learning phase transitions by confusion
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Machine learning vortices at the Kosterlitz-Thouless transition
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• Elastic Lennard-Jones Polymers Meet Clusters -- Differences and Similarities
• Surface effects in the crystallization process of elastic flexible polymers
• Advanced multicanonical Monte Carlo methods for efficient simulations of nucleation processes of polymers
• Two-State Folding, Folding through Intermediates, and Metastability in a Minimalistic Hydrophobic-Polar Model for Proteins
• Conformational phase diagram for polymers adsorbed at ultrathin nanowires
• Structural Arrangements of Polymers Adsorbed at Nanostrings
• Adsorption of polymers at nanowires