Phase Detection with Neural Networks: Interpreting the Black Box

Abstract

Neural networks (NNs) usually hinder any insight into the reasoning behind their predictions. We demonstrate how influence functions can unravel the black box of NN when trained to predict the phases of the one-dimensional extended spinless Fermi-Hubbard model at half-filling. Results provide strong evidence that the NN correctly learns an order parameter describing the quantum transition in this model. We demonstrate that influence functions allow to check that the network, trained to recognize known quantum phases, can predict new unknown ones within the data set. Moreover, we show they can guide physicists in understanding patterns responsible for the phase transition. This method requires no a priori knowledge on the order parameter, has no dependence on the NN's architecture or the underlying physical model, and is therefore applicable to a broad class of physical models or experimental data.

arXiv comment9 pages, 6 figures, example code is available at https://github.com/Shmoo137/Interpretable-Phase-Classification

References in corpus (41)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Machine learning and the physical sciences
• Machine learning phases of matter
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• QuSpin: a Python Package for Dynamics and Exact Diagonalisation of Quantum Many Body Systems part I: spin chains
• Non-standard Hubbard models in optical lattices: a review
• Quantum Entanglement in Neural Network States
• Machine learning quantum phases of matter beyond the fermion sign problem
• Reconstructing quantum states with generative models
• Reinforcement Learning in Different Phases of Quantum Control
• Machine Learning Topological Invariants with Neural Networks
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Machine learning vortices at the Kosterlitz-Thouless transition
• Detection of phase transition via convolutional neural network
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Latent Space Purification via Neural Density Operators
• Kernel methods for interpretable machine learning of order parameters
• A recurrent neural network for classification of unevenly sampled variable stars
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Unsupervised phase discovery with deep anomaly detection
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Unsupervised identification of topological order using predictive models
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• Phase diagram of the half-filled one-dimensional t-V-V' model
• Applications of neural networks to the studies of phase transitions of two-dimensional Potts models
• Automated discovery of characteristic features of phase transitions in many-body localization
• Interpreting machine learning of topological quantum phase transitions
• Divergence of predictive model output as indication of phase transitions
• Visualizing Strange Metallic Correlations in the 2D Fermi-Hubbard Model with AI
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Deep learning of topological phase transitions from entanglement aspects
• Identification of hidden order and emergent constraints in frustrated magnets using tensorial kernel methods
• A machine learning approach to the Berezinskii-Kosterlitz-Thouless transition in classical and quantum models
• Exceptional point induced lasing dynamics in a non-Hermitian system
• Driving Skyrmions in a Composite Bilayer
• Driving Skyrmions on a Composite Multiferroic Lattice

Cited by in corpus (19)

• Artificial Intelligence and Machine Learning for Quantum Technologies
• Machine Learning for Quantum Matter
• Unsupervised machine learning of topological phase transitions from experimental data
• Quantitative and Interpretable Order Parameters for Phase Transitions from Persistent Homology
• Interpretable and unsupervised phase classification
• Entanglement-guided architectures of machine learning by quantum tensor network
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Deep reinforcement learning for key distribution based on quantum repeaters
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Certificates of quantum many-body properties assisted by machine learning
• Morphology of three-body quantum states from machine learning
• Observing a topological phase transition with deep neural networks from experimental images of ultracold atoms
• Deep Learning of Phase Transitions for Quantum Spin Chains from Correlation Aspects
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Deep learning of topological phase transitions from entanglement aspects for two-dimensional chiral p-wave superconductors
• Fluctuation based interpretable analysis scheme for quantum many-body snapshots
• Learning phases with Quantum Monte Carlo simulation cell
• Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
• Neural quantum states for entanglement depth certification from randomized Pauli measurements