Deep neural networks for direct, featureless learning through observation: the case of 2d spin models

Abstract

We demonstrate the capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4x4 Ising model. Using its success at this task, we motivate the study of the larger 8x8 Ising model, showing that the deep neural network can learn the nearest-neighbor Ising Hamiltonian after only seeing a vanishingly small fraction of configuration space. Additionally, we show that the neural network has learned both the energy and magnetization operators with sufficient accuracy to replicate the low-temperature Ising phase transition. We then demonstrate the ability of the neural network to learn other spin models, teaching the convolutional deep neural network to accurately predict the long-range interaction of a screened Coulomb Hamiltonian, a sinusoidally attenuated screened Coulomb Hamiltonian, and a modified Potts model Hamiltonian. In the case of the long-range interaction, we demonstrate the ability of the neural network to recover the phase transition with equivalent accuracy to the numerically exact method. Furthermore, in the case of the long-range interaction, the benefits of the neural network become apparent; it is able to make predictions with a high degree of accuracy, and do so 1600 times faster than a CUDA-optimized exact calculation. Additionally, we demonstrate how the neural network succeeds at these tasks by looking at the weights learned in a simplified demonstration.

References in corpus (5)

• Big Data of Materials Science - Critical Role of the Descriptor
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Learning phase transitions by confusion
• Deep learning and the Schrödinger equation
• Machine learning for many-body physics: The case of the Anderson impurity model

Cited by in corpus (18)

• Regressive and generative neural networks for scalar field theory
• Solving frustrated quantum many-particle models with convolutional neural networks
• Deep Learning and AdS/CFT
• Machine-learning inference of fluid variables from data using reservoir computing
• Extensive deep neural networks for transferring small scale learning to large scale systems
• Smallest Neural Network to Learn the Ising Criticality
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Few-shot machine learning in the three-dimensional Ising model
• Self-organizing maps as a method for detecting phase transitions and phase identification
• Can a CNN trained on the Ising model detect the phase transition of the $q$-state Potts model?
• Optical lattice experiments at unobserved conditions and scales through generative adversarial deep learning
• Visualizing Neural Network Developing Perturbation Theory
• Probing Criticality in Quantum Spin Chains with Neural Networks
• Watch and learn -- a generalized approach for transferrable learning in deep neural networks via physical principles
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• Global exploration of phase behavior in frustrated Ising models using unsupervised learning techniques
• Machine-learning semi-local density functional theory for many-body lattice models at zero and finite temperature