Smallest neural network to learn the Ising criticality.

Learning with an artificial neural network encodes the system behavior in a feed-forward function with a number of parameters optimized by data-driven training. An open question is whether one can minimize the network complexity without loss of performance to reveal how and why it works. Here we investigate the learning of the phase transition in the Ising model and find that having two hidden neurons can be enough for an accurate prediction of critical temperature. We show that the networks learn the scaling dimension of the order parameter while being trained as a phase classifier, demonstrating how the machine learning exploits the Ising universality to work for different lattices of the same criticality within a single set of trainings in one lattice geometry.

[1]  A. Tanaka,et al.  Detection of phase transition via convolutional neural network , 2016, 1609.09087.

[2]  Yang Qi,et al.  Self-learning Monte Carlo method and cumulative update in fermion systems , 2017 .

[3]  Pengfei Zhang,et al.  Machine Learning Topological Invariants with Neural Networks , 2017, Physical review letters.

[4]  Tomi Ohtsuki,et al.  Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems , 2016, 1610.00462.

[5]  D. Deng,et al.  Quantum Entanglement in Neural Network States , 2017, 1701.04844.

[6]  Yang Qi,et al.  Self-learning Monte Carlo method , 2016, 1610.03137.

[7]  Kelvin George Chng,et al.  Unsupervised machine learning account of magnetic transitions in the Hubbard model. , 2017, Physical review. E.

[8]  Roger G. Melko,et al.  Machine learning phases of matter , 2016, Nature Physics.

[9]  Yang Qi,et al.  Self-learning quantum Monte Carlo method in interacting fermion systems , 2017 .

[10]  D. Landau,et al.  Efficient, multiple-range random walk algorithm to calculate the density of states. , 2000, Physical review letters.

[11]  Matthias Troyer,et al.  Neural-network quantum state tomography , 2018 .

[12]  Isaac Tamblyn,et al.  Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models. , 2017, Physical review. E.

[13]  Yi Zhang,et al.  Quantum Loop Topography for Machine Learning. , 2016, Physical review letters.

[14]  Jinguo Liu,et al.  Approximating quantum many-body wave functions using artificial neural networks , 2017, 1704.05148.

[15]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[16]  Roger G. Melko,et al.  Machine learning vortices at the Kosterlitz-Thouless transition , 2017, 1710.09842.

[17]  Lei Wang,et al.  Discovering phase transitions with unsupervised learning , 2016, 1606.00318.

[18]  Yi Zhang,et al.  Machine learning Z 2 quantum spin liquids with quasiparticle statistics , 2017, 1705.01947.

[19]  Titus Neupert,et al.  Probing many-body localization with neural networks , 2017, 1704.01578.

[20]  Richard T. Scalettar,et al.  Principal component analysis for fermionic critical points , 2017 .

[21]  D. Landau,et al.  Determining the density of states for classical statistical models: a random walk algorithm to produce a flat histogram. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[22]  Lu-Ming Duan,et al.  Efficient representation of quantum many-body states with deep neural networks , 2017, Nature Communications.

[23]  Roger G. Melko,et al.  Kernel methods for interpretable machine learning of order parameters , 2017, 1704.05848.

[24]  J. Cirac,et al.  Neural-Network Quantum States, String-Bond States, and Chiral Topological States , 2017, 1710.04045.

[25]  Peter Wittek,et al.  Adversarial Domain Adaptation for Identifying Phase Transitions , 2017, ArXiv.

[26]  J. Chen,et al.  Equivalence of restricted Boltzmann machines and tensor network states , 2017, 1701.04831.

[27]  T. Ohtsuki,et al.  Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions , 2016, 1612.04909.

[28]  Satoshi Iso,et al.  Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow , 2018, Physical review. E.

[29]  Li Huang,et al.  Accelerated Monte Carlo simulations with restricted Boltzmann machines , 2016, 1610.02746.

[30]  S. Rychkov,et al.  Solving the 3d Ising Model with the Conformal Bootstrap II. $$c$$c-Minimization and Precise Critical Exponents , 2012, 1403.4545.

[31]  Wooseop Kwak,et al.  First-order phase transition and tricritical scaling behavior of the Blume-Capel model: A Wang-Landau sampling approach. , 2015, Physical review. E, Statistical, nonlinear, and soft matter physics.

[32]  Roger G. Melko,et al.  Learning Thermodynamics with Boltzmann Machines , 2016, ArXiv.

[33]  Juan Carrasquilla,et al.  Machine learning quantum phases of matter beyond the fermion sign problem , 2016, Scientific Reports.

[34]  R. Melko,et al.  Machine Learning Phases of Strongly Correlated Fermions , 2016, Physical Review X.

[35]  Sebastian Johann Wetzel,et al.  Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders , 2017, Physical review. E.

[36]  D. Landau,et al.  A new approach to Monte Carlo simulations in statistical physics: Wang-Landau sampling , 2004 .

[37]  Martin Hasenbusch,et al.  Finite size scaling study of lattice models in the three-dimensional Ising universality class , 2010, 1004.4486.

[38]  Wolff,et al.  Collective Monte Carlo updating for spin systems. , 1989, Physical review letters.

[39]  Zohar Ringel,et al.  Mutual information, neural networks and the renormalization group , 2017, ArXiv.

[40]  Yang Qi,et al.  Self-learning Monte Carlo method: Continuous-time algorithm , 2017, 1705.06724.

[41]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[42]  Qiong Zhu,et al.  Identifying Product Order with Restricted Boltzmann Machines , 2017, 1709.02597.

[43]  Chris Beeler,et al.  Extensive deep neural networks for transferring small scale learning to large scale systems , 2017, Chemical science.

[44]  Ye-Hua Liu,et al.  Discriminative Cooperative Networks for Detecting Phase Transitions. , 2017, Physical review letters.

[45]  Lei Wang,et al.  Exploring cluster Monte Carlo updates with Boltzmann machines. , 2017, Physical review. E.

[46]  Stefan Wessel,et al.  Parameter diagnostics of phases and phase transition learning by neural networks , 2018, Physical Review B.

[47]  Hui Zhai,et al.  Deep learning topological invariants of band insulators , 2018, Physical Review B.

[48]  Manuel Scherzer,et al.  Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory , 2017, 1705.05582.

[49]  Tanaka Akinori,et al.  Detection of Phase Transition via Convolutional Neural Networks , 2016, 1609.09087.

[50]  Wenjian Hu,et al.  Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination. , 2017, Physical review. E.

[51]  Andrew S. Darmawan,et al.  Restricted Boltzmann machine learning for solving strongly correlated quantum systems , 2017, 1709.06475.

[52]  Matthias Troyer,et al.  Solving the quantum many-body problem with artificial neural networks , 2016, Science.

[53]  S. Huber,et al.  Learning phase transitions by confusion , 2016, Nature Physics.