Abstract
Symbolic Regression (SR) is emerging as a promising machine learning tool to directly learn succinct, mathematical and interpretable expressions directly from data. The combination of SR with deep learning (e.g. Graph Neural Network and Autoencoders) provides a powerful toolkit for scientists to push the frontiers of scientific discovery in a data-driven manner. We briefly overview SR, autoencoders and GNN and highlight examples where they have been used to rediscover known physical phenomenon directly from data.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Technically the pseudo-inverse, \(U^{+}\).
References
Cranmer, M., et al.: Discovering symbolic models from deep learning with inductive biases. arXiv:2006.11287 [cs.LG]
Champion, K., Lusch, B., Kutz, J.N., Brunton, S.L.: Data-driven discovery of coordinates and governing equations. PNAS 116(45), 22445–22451 (2019). https://doi.org/10.1073/pnas.1906995116
La Cava, W., et al.: Contemporary symbolic regression methods and their relative performance. In: NeurIPS 2021 Datasets and Benchmarks Track (Round 1) (2021)
Halzen, F., Martin, A.D.: Quarks and Leptons: An Introductory Course in Modern Particle Physics. Willey, Hoboken (1984)
Udrescu, S.M., Tegmark, M.: AI Feynman: a physics-inspired method for symbolic regression. Sci. Adv. 6(16), eaay2631 (2020). https://doi.org/10.1126/sciadv.aay2631
Petersen, B.K., Larma, M.L., Mundhenk, T.N., Santiago, C.P, Kim, S.K., Kim, J.T.: Deep symbolic regression: recovering mathematical expressions from data via risk-seeking policy gradients. In: International Conference on Learning Representations (2021)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. ArXiv:1806.01261 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Makke, N., Sadeghi, M.A., Chawla, S. (2022). Symbolic Regression for Interpretable Scientific Discovery. In: Sachdeva, S., Watanobe, Y., Bhalla, S. (eds) Big-Data-Analytics in Astronomy, Science, and Engineering. BDA 2021. Lecture Notes in Computer Science(), vol 13167. Springer, Cham. https://doi.org/10.1007/978-3-030-96600-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-96600-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96599-0
Online ISBN: 978-3-030-96600-3
eBook Packages: Computer ScienceComputer Science (R0)