Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks

In this paper, we introduce interpretable Siamese Neural Networks (SNN) for similarity detection to the field of theoretical physics. More precisely, we apply SNNs to events in special relativity, the transformation of electromagnetic fields, and the motion of particles in a central potential. In these examples, the SNNs learn to identify datapoints belonging to the same events, field configurations, or trajectory of motion. It turns out that in the process of learning which datapoints belong to the same event or field configuration, these SNNs also learn the relevant symmetry invariants and conserved quantities. These SNNs are highly interpretable, which enables us to reveal the symmetry invariants and conserved quantities without prior knowledge.

[1]  Dong-Ling Deng,et al.  Machine Learning Topological States , 2016, 1609.09060.

[2]  Renato Renner,et al.  Discovering physical concepts with neural networks , 2018, Physical review letters.

[3]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[4]  Jan M. Pawlowski,et al.  Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning , 2020, ArXiv.

[5]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

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

[7]  Thomas G. Dietterich,et al.  In Advances in Neural Information Processing Systems 12 , 1991, NIPS 1991.

[8]  John R. Koza,et al.  Genetic programming as a means for programming computers by natural selection , 1994 .

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

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

[11]  Hod Lipson,et al.  Distilling Free-Form Natural Laws from Experimental Data , 2009, Science.

[12]  小谷 正雄.  日本物理学会誌及びJournal of the Physical Society of Japanの月刊について , 1955 .

[13]  R. Kennedy,et al.  Defense Advanced Research Projects Agency (DARPA). Change 1 , 1996 .

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

[15]  Max Tegmark,et al.  AI Feynman: A physics-inspired method for symbolic regression , 2019, Science Advances.

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

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

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

[19]  Amnon Shashua,et al.  Deep autoregressive models for the efficient variational simulation of many-body quantum systems , 2019, Physical review letters.

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

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

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

[23]  W. Marsden.  I and J , 2012 .

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

[25]  Mohamed Hibat-Allah,et al.  Recurrent Neural Network Wavefunctions , 2020 .

[26]  E. M. Inack,et al.  Projective quantum Monte Carlo simulations guided by unrestricted neural network states , 2018, Physical Review B.

[27]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[28]  Ce Wang,et al.  Emergent Schrödinger equation in an introspective machine learning architecture , 2019 .

[29]  Wojciech Samek,et al.  Methods for interpreting and understanding deep neural networks , 2017, Digit. Signal Process..

[30]  Dongkyu Kim,et al.  Smallest neural network to learn the Ising criticality. , 2018, Physical review. E.

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

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

[33]  Hui Zhai,et al.  Emergent Quantum Mechanics in an Introspective Machine Learning Architecture , 2019 .

[34]  J. Carrasquilla,et al.  Neural Gutzwiller-projected variational wave functions , 2019, Physical Review B.

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

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

[37]  P. Ginsparg,et al.  Interpreting machine learning of topological quantum phase transitions , 2019, 1912.10057.

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

[39]  Ke Liu,et al.  Probing hidden spin order with interpretable machine learning , 2018, Physical Review B.