- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Letter
  • Open Access

Similarity-based equational inference in physics

Jordan Meadows1,* and André Freitas1,2,†

  • 1Department of Computer Science, University of Manchester, Manchester M13 9PL, United Kingdom
  • 2Idiap Research Institute, Rue Marconi 19, 1920 Martigny, Switzerland

  • *jordan.meadows@postgrad.manchester.ac.uk
  • †andre.freitas@manchester.ac.uk
PDF

Phys. Rev. Research 3, L042010 – Published 28 October, 2021

DOI: https://doi.org/10.1103/PhysRevResearch.3.L042010

Abstract

Automating the derivation of published results is a challenge, in part due to the informal use of mathematics by physicists compared to that of mathematicians. Following demand, we describe a method for converting informal handwritten derivations into datasets and present an example dataset crafted from a contemporary result in condensed matter. We define an equation reconstruction task completed by rederiving an unknown intermediate equation posed as a state, taken from three consecutive equational states within a derivation. Derivation automation is achieved via computer algebra system (CAS) by applying string-based CAS-reliant actions to states, which mimic mathematical operations and induce state transitions. We implement a symbolic similarity-based heuristic search to solve the equation reconstruction task as an early step towards multi-hop equational inference in physics.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (28)

  1. G. Kissas, Y. Yang, E. Hwuang, W. R. Witschey, J. A. Detre, and P. Perdikaris, Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4d flow MRI data using physics-informed neural networks, Comput. Methods Appl. Mech. Eng. 358, 112623 (2020).
  2. J. Liang and X. Zhu, Phillips-inspired machine learning for band gap and exciton binding energy prediction, J. Phys. Chem. Lett. 10, 5640 (2019).
  3. G. H. Teichert, A. Natarajan, A. Van der Ven, and K. Garikipati, Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions, Comput. Methods Appl. Mech. Eng. 353, 201 (2019).
  4. J. Collins, K. Howe, and B. Nachman, Anomaly Detection for Resonant New Physics With Machine Learning, Phys. Rev. Lett. 121, 241803 (2018).
  5. T. Bereau, R. A. DiStasio Jr, A. Tkatchenko, and O. A. Von Lilienfeld, Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning, J. Chem. Phys. 148, 241706 (2018).
  6. G. Torlai, G. Mazzola, J. Carrasquilla, M. Troyer, R. Melko, and G. Carleo, Neural-network quantum state tomography, Nat. Phys. 14, 447 (2018).
  7. S.-M. Udrescu and M. Tegmark, Symbolic pregression: Discovering physical laws from raw distorted video, Phys. Rev. E 103, 043307 (2021).
  8. S.-M. Udrescu, A. Tan, J. Feng, O. Neto, T. Wu, and M. Tegmark, Ai Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity, arXiv:2006.10782.
  9. S. Kim, P. Y. Lu, S. Mukherjee, M. Gilbert, L. Jing, V. Čeperić, and M. Soljačić, Integration of neural network-based symbolic regression in deep learning for scientific discovery, IEEE Trans. Neural Networks Learn. Syst. 32, 4166 (2020).
  10. R. Iten, T. Metger, H. Wilming, L. del Rio, and R. Renner, Discovering Physical Concepts With Neural Networks, Phys. Rev. Lett. 124, 010508 (2020).
  11. E. Davis, Proof verification technology and elementary physics, in Algorithms and Complexity in Mathematics, Epistemology, and Science (Springer, New York, 2019), pp. 81–132.
  12. C. Kaliszyk, J. Urban, U. Siddique, S. Khan-Afshar, C. Dunchev, and S. Tahar, Formalizing physics: Automation, presentation and foundation issues, in International Conference on Intelligent Computer Mathematics (Springer, New York, 2015), pp. 288–295.
  13. N. S. Govindarajalulu, S. Bringsjord, and J. Taylor, Proof verification and proof discovery for relativity, Synthese 192, 2077 (2015).
  14. C.-R. Mann, T. J. Sturges, G. Weick, W. L. Barnes, and E. Mariani, Manipulating type-I and type-II Dirac polaritons in cavity-embedded honeycomb metasurfaces, Nat. Commun. 9, 2194 (2018).
  15. https://github.com/jmeadows17/equational-inference (unpublished).
  16. J.-L. Wu, H. Xiao, and E. Paterson, Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework, Phys. Rev. Fluids 3, 074602 (2018).
  17. V. L. Deringer and G. Csányi, Machine learning based interatomic potential for amorphous carbon, Phys. Rev. B 95, 094203 (2017).
  18. R. Ramakrishnan, P. O. Dral, M. Rupp, and O. A. von Lilienfeld, Big data meets quantum chemistry approximations: The δ-machine learning approach, J. Chem. Theory Comput. 11, 2087 (2015).
  19. P. Baldi, P. Sadowski, and D. Whiteson, Searching for exotic particles in high-energy physics with deep learning, Nat. Commun. 5, 4308 (2014).
  20. T. Wu and M. Tegmark, Toward an artificial intelligence physicist for unsupervised learning, Phys. Rev. E 100, 033311 (2019).
  21. M. Raissi and G. E. Karniadakis, Hidden physics models: Machine learning of nonlinear partial differential equations, J. Comput. Phys. 357, 125 (2018).
  22. Z. Zhang, Y. Zhao, J. Liu, S. Wang, R. Tao, R. Xin, and J. Zhang, A general deep learning framework for network reconstruction and dynamics learning, Appl. Network Sci. 4, 110 (2019).
  23. C. Kaliszyk, J. Urban, H. Michalewski, and M. Olšák, Reinforcement learning of theorem proving, arXiv:1805.07563.
  24. J. Piepenbrock, T. Heskes, M. Janota, and J. Urban, Learning equational theorem proving, arXiv:2102.05547.
  25. M. Luo and L. Liu, Automatic derivation of formulas using reforcement learning, arXiv:1808.04946.
  26. S. Min, E. Wallace, S. Singh, M. Gardner, H. Hajishirzi, and L. Zettlemoyer, Compositional questions do not necessitate multihop reasoning, arXiv:1906.02900.
  27. A. Meurer, C. P. Smith, M. Paprocki, O. Čertík, S. B. Kirpichev, M. Rocklin, A. Kumar, S. Ivanov, J. K. Moore, S. Singh et al., sympy: Symbolic computing in python, Peer J. Comput. Sci. 3, e103 (2017).
  28. D. Ferreira and A. Freitas, Premise selection in natural language mathematical texts, in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (Association for Computational Linguistics, 2020), pp. 7365–7374.

Outline

Information

Phys. Rev. Research 3, L042010– Published 28 October, 2021
  • Received 25 March 2021
  • Accepted 21 June 2021
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation