Machine learning vortices at the Kosterlitz-Thouless transition
arXiv:1710.09842 · doi:10.1103/PhysRevB.97.045207
Abstract
Efficient and automated classification of phases from minimally processed data is one goal of machine learning in condensed matter and statistical physics. Supervised algorithms trained on raw samples of microstates can successfully detect conventional phase transitions via learning a bulk feature such as an order parameter. In this paper, we investigate whether neural networks can learn to classify phases based on topological defects. We address this question on the two-dimensional classical XY model which exhibits a Kosterlitz-Thouless transition. We find significant feature engineering of the raw spin states is required to convincingly claim that features of the vortex configurations are responsible for learning the transition temperature. We further show a single-layer network does not correctly classify the phases of the XY model, while a convolutional network easily performs classification by learning the global magnetization. Finally, we design a deep network capable of learning vortices without feature engineering. We demonstrate the detection of vortices does not necessarily result in the best classification accuracy, especially for lattices of less than approximately 1000 spins. For larger systems, it remains a difficult task to learn vortices.
8 pages, 7 figures
References in corpus (7)
- Deep Learning in Neural Networks: An Overview
- Learning phase transitions by confusion
- Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
- Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
- Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
- An introduction to Monte Carlo methods
- Large-scale Monte Carlo simulation of two-dimensional classical XY model using multiple GPUs