The DOI matches its Crossref record; 82 of the 82 references it cites were found in a registry or an index.
Discovering Physical Concepts with Neural Networks
Open accessAbstract
Despite the success of neural networks at solving concrete physics problems, their use as a general-purpose tool for scientific discovery is still in its infancy. Here, we approach this problem by modeling a neural network architecture after the human physical reasoning process, which has similarities to representation learning. This allows us to make progress towards the long-term goal of machine-assisted scientific discovery from experimental data without making prior assumptions about the system. We apply this method to toy examples and show that the network finds the physically relevant parameters, exploits conservation laws to make predictions, and can help to gain conceptual insights, e.g., Copernicus' conclusion that the solar system is heliocentric.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Raissi, M., Perdikaris, P., & Karniadakis, G. E. (2019) · Journal of Computational Physics · doi:10.1016/j.jcp.2018.10.045 · Cited by 20,384
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,887
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Quantum Computation and Quantum Information: 10th Anniversary Edition
Nielsen, M. A., & Chuang, I. L. (2012) · doi:10.1017/cbo9780511976667 · Cited by 8,436
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091
Discovering governing equations from data by sparse identification of nonlinear dynamical systems
Brunton, S. L., Proctor, J. L., & Kutz, J. N. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1517384113 · Cited by 4,796
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015) · arXiv · doi:10.48550/arxiv.1511.07289 · Cited by 4,513
(2017) · International Conference on Learning Representations · Cited by 3,248
Distilling Free-Form Natural Laws from Experimental Data
Schmidt, M., & Lipson, H. (2009) · Science · doi:10.1126/science.1165893 · Cited by 2,890
Quantum Computation and Quantum Information: 10th Anniversary Edition
Nielsen, M. A., & Chuang, I. L. (2011) · Cited by 2,724
The information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626 · cited 1×
“Hence, methods from standard information theory, like the information bottleneck [7], are not the right tool to give the number of variables a formal meaning.”
MethodBreakdown of predictability in gravitational collapse
Hawking, S. W. (1976) · Physical Review D · doi:10.1103/physrevd.14.2460 · Cited by 2,554
Building machines that learn and think like people
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017) · Behavioral and Brain Sciences · doi:10.1017/s0140525x16001837 · Cited by 2,550
2013 IEEE Conference on Computer Vision and Pattern Recognition
(2013) · doi:10.1109/cvpr19808.2013 · Cited by 2,396
Introduction to Smooth Manifolds
Lee, J. M. (2012) · Graduate Texts in Mathematics · doi:10.1007/978-1-4419-9982-5 · Cited by 2,296
Solving the quantum many-body problem with artificial neural networks
Carleo, G., & Troyer, M. (2017) · Science · doi:10.1126/science.aag2302 · Cited by 2,215
Genetic programming as a means for programming computers by natural selection
Koza, J. (1994) · Statistics and Computing · doi:10.1007/bf00175355 · Cited by 1,685
Deep learning for universal linear embeddings of nonlinear dynamics
Lusch, B., Kutz, J. N., & Brunton, S. L. (2018) · Nature Communications · doi:10.1038/s41467-018-07210-0 · Cited by 1,424
Deep learning and the information bottleneck principle
Tishby, N., & Zaslavsky, N. (2015) · 2015 IEEE Information Theory Workshop (ITW) · doi:10.1109/itw.2015.7133169 · Cited by 1,409
Hidden physics models: Machine learning of nonlinear partial differential equations
Raissi, M., & Karniadakis, G. E. (2018) · Journal of Computational Physics · doi:10.1016/j.jcp.2017.11.039 · Cited by 1,349
Interaction Networks for Learning about Objects, Relations and Physics
Battaglia, P. W., Pascanu, R., Lai, M., Rezende, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1612.00222 · Cited by 969
Neural-network quantum state tomography
Torlai, G., Mazzola, G., Carrasquilla, J., Troyer, M., Melko, R., & Carleo, G. (2018) · Nature Physics · doi:10.1038/s41567-018-0048-5 · Cited by 843
Proceedings of the 28th International Conference on Neural Information Processing Systems
Cortes, C., Lee, D., Sugiyama, M., & Garnett, R. (2015) · Cited by 747
Simulation as an engine of physical scene understanding
Battaglia, P. W., Hamrick, J. B., & Tenenbaum, J. B. (2013) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1306572110 · Cited by 681
Kim, H., & Mnih, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.05983 · Cited by 617
Deep Learning of Representations: Looking Forward
Bengio, Y. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-39593-2_1 · Cited by 513
Neural scene representation and rendering
Eslami, S. M. A., Jimenez Rezende, D., Besse, F., Viola, F., Morcos, A. S., Garnelo, M., Ruderman, A., Rusu, A. A., Danihelka, I., Gregor, K., et al. (2018) · Science · doi:10.1126/science.aar6170 · Cited by 495
Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery
Gade, R., Jorgensen, A., & Moeslund, T. B. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.474 · Cited by 437
Neural Networks and Deep Learning: A Textbook
Aggarwal, C. C. (2018) · doi:10.1007/978-3-319-94463-0 · Cited by 417
Quantum Entanglement in Neural Network States
Deng, D.-L., Li, X., & Das Sarma, S. (2017) · Physical Review X · doi:10.1103/physrevx.7.021021 · Cited by 403
A Compositional Object-Based Approach to Learning Physical DynamicsPreprint
Chang, M. B., Ullman, T. D., Torralba, A. B., & Tenenbaum, J. B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.00341 · Cited by 388
Information dropout: learning optimal representations through noisy computation
Achille, A., & Soatto, S. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2784440 · Cited by 356
Efficient representation of quantum many-body states with deep neural networks
Gao, X., & Duan, L.-M. (2017) · Nature Communications · doi:10.1038/s41467-017-00705-2 · Cited by 346
Linearly Recurrent Autoencoder Networks for Learning Dynamics
Otto, S. E., & Rowley, C. W. (2019) · SIAM Journal on Applied Dynamical Systems · doi:10.1137/18m1177846 · Cited by 345
Restricted Boltzmann machine learning for solving strongly correlated quantum systems
Nomura, Y., Darmawan, A. S., Yamaji, Y., & Imada, M. (2017) · Physical Review B · doi:10.1103/physrevb.96.205152 · Cited by 318
Reconstructing quantum states with generative models
Carrasquilla, J., Torlai, G., Melko, R. G., & Aolita, L. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0028-1 · Cited by 317
Active learning machine learns to create new quantum experiments
Melnikov, A. A., Poulsen Nautrup, H., Krenn, M., Dunjko, V., Tiersch, M., Zeilinger, A., & Briegel, H. J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1714936115 · Cited by 296
Understanding disentangling in $\beta$-VAEPreprint
Burgess, C., Higgins, I., Pal, A., Matthey, L., Watters, N., Desjardins, G., & Lerchner, A. (2018) · arXiv (Cornell University) · Cited by 294
Machine learning topological states
Deng, D.-L., Li, X., & Das Sarma, S. (2017) · Physical Review B · doi:10.1103/physrevb.96.195145 · Cited by 290
Learning Koopman Invariant Subspaces for Dynamic Mode DecompositionPreprint
Takeishi, N., Kawahara, Y., & Yairi, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.04340 · Cited by 271
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning
Wu, J., Yildirim, I., Lim, J. J., Freeman, W. T., & Tenenbaum, J. B. (2016) · Cited by 264
Learning thermodynamics with Boltzmann machines
Torlai, G., & Melko, R. G. (2016) · Physical Review B · doi:10.1103/physrevb.94.165134 · Cited by 252
Neural-Network Quantum States, String-Bond States, and Chiral Topological States
Glasser, I., Pancotti, N., August, M., Rodríguez, I., & Cirac, J. I. (2018) · Max Planck Digital Library · Cited by 250
Quantum theory cannot consistently describe the use of itself
Frauchiger, D., & Renner, R. (2018) · RePEc: Research Papers in Economics · doi:10.3929/ethz-b-000293141 · Cited by 241
Self-citationAutomated Search for new Quantum Experiments
Krenn, M., Malik, M., Fickler, R., Lapkiewicz, R., & Zeilinger, A. (2016) · Physical Review Letters · doi:10.1103/physrevlett.116.090405 · Cited by 238
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
Fraccaro, M., Kamronn, S., Paquet, U., & Winther, O. (2017) · arXiv · doi:10.48550/arxiv.1710.05741 · Cited by 229
Approximating quantum many-body wave functions using artificial neural networks
Cai, Z., & Liu, J. (2018) · Physical Review B · doi:10.1103/physrevb.97.035116 · Cited by 214
Neural-Network Quantum States, String-Bond States, and Chiral Topological States
Glasser, I., Pancotti, N., August, M., Rodriguez, I. D., & Cirac, J. I. (2018) · Physical Review X · doi:10.1103/physrevx.8.011006 · Cited by 214
Learning new physics from a machine
D’Agnolo, R. T., & Wulzer, A. (2019) · Physical Review D · doi:10.1103/physrevd.99.015014 · Cited by 203
Efficient representation of quantum many-body states with deep neural networks
Gao, X., & Duan, L.-M. (2017) · RePEc: Research Papers in Economics · Cited by 202
Constructing exact representations of quantum many-body systems with deep neural networks
Carleo, G., Nomura, Y., & Imada, M. (2018) · Nature Communications · doi:10.1038/s41467-018-07520-3 · Cited by 201
Automated adaptive inference of phenomenological dynamical models
Daniels, B. C., & Nemenman, I. (2015) · Nature Communications · doi:10.1038/ncomms9133 · Cited by 194
Mutual information, neural networks and the renormalization group
Koch-Janusz, M., & Ringel, Z. (2018) · Nature Physics · doi:10.1038/s41567-018-0081-4 · Cited by 192
Projective simulation for artificial intelligence
Briegel, H. J., & Cuevas, G. D. L. (2012) · Scientific Reports · doi:10.1038/srep00400 · Cited by 181
Constructing exact representations of quantum many-body systems with deep neural networks
Carleo, G., Nomura, Y., & Imada, M. (2018) · RePEc: Research Papers in Economics · doi:10.3929/ethz-b-000313237 · Cited by 156
Automated refinement and inference of analytical models for metabolic networks
Schmidt, M. D., Vallabhajosyula, R. R., Jenkins, J. W., Hood, J. E., Soni, A. S., Wikswo, J. P., & Lipson, H. (2011) · Physical Biology · doi:10.1088/1478-3975/8/5/055011 · Cited by 144
Guiding new physics searches with unsupervised learning
Andrea De Simone, A., & Jacques, T. (2019) · The European Physical Journal C · doi:10.1140/epjc/s10052-019-6787-3 · Cited by 140
Neural Network Representation of Tensor Network and Chiral States
Huang, Y., & Moore, J. E. (2021) · Physical Review Letters · doi:10.1103/physrevlett.127.170601 · Cited by 136
Learning hard quantum distributions with variational autoencoders
Rocchetto, A., Grant, E., Strelchuk, S., Carleo, G., & Simone Severini, B. (2018) · npj Quantum Information · doi:10.1038/s41534-018-0077-z · Cited by 106
Discovering objects and their relations from entangled scene representationsPreprint
Raposo, D. C., Santoro, A., Barrett, D. G. T., Pascanu, R., Lillicrap, T., & Battaglia, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.05068 · Cited by 103
Toward an artificial intelligence physicist for unsupervised learning
Wu, T., & Tegmark, M. (2019) · Physical Review E · doi:10.1103/physreve.100.033311 · Cited by 99
Ohtsuki, T., & Ohtsuki, T. (2017) · Journal of the Physical Society of Japan · doi:10.7566/jpsj.86.044708 · Cited by 78
Intuitive experimentation in the physical world
Bramley, N. R., Gerstenberg, T., Tenenbaum, J. B., & Gureckis, T. M. (2018) · Cognitive Psychology · doi:10.1016/j.cogpsych.2018.05.001 · Cited by 73
Learning physical parameters from dynamic scenes
Ullman, T. D., Stuhlmüller, A., Goodman, N. D., & Tenenbaum, J. B. (2018) · Cognitive Psychology · doi:10.1016/j.cogpsych.2017.05.006 · Cited by 72
Learning hard quantum distributions with variational autoencoders
Rocchetto, A., Grant, E., Strelchuk, S., Carleo, G., & Simone Severini, B. (2018) · UCL Discovery (University College London) · doi:10.3929/ethz-b-000276431 · Cited by 69
Quantum dynamics in transverse-field Ising models from classical networks
Schmitt, M., & Heyl, M. (2018) · SciPost Physics · doi:10.21468/scipostphys.4.2.013 · Cited by 66
2015 IEEE Information Theory Workshop (ITW)
(2015) · doi:10.1109/itw33791.2015 · Cited by 62
Unsupervised Learning of Latent Physical Properties Using Perception-Prediction NetworksPreprint
Zheng, D., Luo, V., Wu, J., & Tenenbaum, J. B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.09244 · Cited by 61
Quantum dynamics in transverse-field Ising models from classical networks
Schmitt, M., & Heyl, M. (2018) · Max Planck Digital Library · Cited by 60
Learning phase transitions from dynamics
van Nieuwenburg, E., Bairey, E., & Refael, G. (2018) · Physical review. B./Physical review. B · doi:10.1103/physrevb.98.060301 · Cited by 59
Humans predict liquid dynamics using probabilistic simulation.
Bates, C., Battaglia, P., Yildirim, I., & Tenenbaum, J. B. (2015) · Cited by 56
Automated discovery of characteristic features of phase transitions in many-body localization
Huembeli, P., Dauphin, A., Wittek, P., & Gogolin, C. (2019) · Physical review. B./Physical review. B · doi:10.1103/physrevb.99.104106 · Cited by 54
Extracting Dynamical Equations from Experimental Data is NP Hard
Cubitt, T. S., Eisert, J., & Wolf, M. M. (2012) · Physical Review Letters · doi:10.1103/physrevlett.108.120503 · Cited by 52
QuCumber: wavefunction reconstruction with neural networks
Beach, M. J. S., Vlugt, I. J. S. D., Golubeva, A., Huembeli, P., Kulchytskyy, B., Luo, X., Melko, R. G., Merali, E., & Torlai, G. (2019) · SciPost Physics · doi:10.21468/scipostphys.7.1.009 · Cited by 45
Autoencoding topologyPreprint
Korman, E. O. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.00156 · Cited by 14
Opening the Black Box of Deep Neural Networks via Information
Shwartz-Ziv, R., & Tishby, N. (2017) · arXiv · doi:10.48550/arxiv.1703.00810
Research works printed but not linked: 6
- J. B. Hamrick, 2011, Proceedings of the 33rd Annual Conference of the Cognitive Science Society Austin, TX
- J. P. Crutchfield, 1987, Complex Syst., 1, 417
- C. Bates, 2015, Proceedings of the 37th Annual Conference of the Cognitive Science Society, Pasadena, CA
- J. Wu, 2015, Advances in Neural Information Processing Systems 28
- I. Higgins, 2017, ICLR, 2, 1
- 2004, Lecture Notes in Physics
Cited by
Physics-informed machine learning
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00314-5 · Cited by 8,718
Explainable machine learning for scientific insights and discoveries
Roscher, R., Bohn, B., Duarte, M. F., & Garcke, J. (2020) · IEEE Access · doi:10.1109/access.2020.2976199 · Cited by 1,040
“Reference [100] introduces SciNet, a modified variational autoencoder that learns a representation from experimental data and uses the learned representation to derive physical concepts from it rather than from the experimental input”
BackgroundHart, G. L. W., Mueller, T., Toher, C., & Curtarolo, S. (2021) · Nature Reviews Materials · doi:10.1038/s41578-021-00340-w · Cited by 703
Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation
Krenn, M., Häse, F., Nigam, A., Friederich, P., & Aspuru-Guzik, A. (2020) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/aba947 · Cited by 660
Jusup, M., Holme, P., Kanazawa, K., Takayasu, M., Romić, I., Wang, Z., Geček, S., Lipić, T., Podobnik, B., Wang, L., et al. (2022) · Physics Reports · doi:10.1016/j.physrep.2021.10.005 · Cited by 643
Metadata
- Authors
- Iten, R., Metger, T., Wilming, H., del Rio, L., & Renner, R.
- Venue
- Physical Review Letters
- Publisher
- American Physical Society (APS)
- Published
- 2020-01-08
- Volume
- 124
- Issue
- 1
- Pages
- 010508-010508
- ISSN
- 0031-9007 (ISSN-L)
- 1079-7114
- OpenAlex
- W2884775584
- Cited by
- 458
- References
- 82
- FWCI
- 35.17
- Type
- journal article
- Language
- en
- Open access
- green
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (200020_165843)
- Foundational Questions Institute
- Eidgenössische Technische Hochschule Zürich
- Swiss National Supercomputing Centre
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.