RIKEN Center for Advanced Intelligence Project Computational Physics Machine Learning Team
Team Director: Takaharu Yaguchi (Ph.D.)
Research Summary
From around 2019, scientific machine learning, which is a new research field that combines machine learning and scientific computing, has emerged. The scientific machine learning methods are expected to enable the simulation of phenomena for which the governing equations are unknown, and to accelerate physical simulations greatly. Our team develops, particularly, methods that respect laws of physics such as the energy conservation law and also performs theoretical analysis, in order to develop reliable scientific machine learning methods.
Main Research Fields
- Interdisciplinary Science & Engineering
Related Research Fields
- Engineering
- Informatics
- Mathematical & Physical Sciences
- Computational science-related
- Intelligent informatics-related
- Intelligent informatics-related
Keywords
- Scientific Machine Learning
- Machine Learning for Physics
- Operator Learning
- Physical Simulation
- Physical Modeling
Selected Publications
Papers with an asterisk(*) are based on research conducted outside of RIKEN.
- 1.
Tanaka, Y., Iwata, T., Ueda, N., Yaguchi, T.
"Energy-Consistent Neural Operators for Hamiltonian and Dissipative Partial Differential Equations"
Proc. of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS2025), (2025) - 2.
*Khosrovian, R. A. , Yaguchi, T., Yoshimura, H., Matsubara, T.
"Poisson-Dirac Neural Networks for Modeling Coupled Dynamical Systems across Domains"
Proc. of the Thirteenth International Conference on Learning Representations (ICLR2025), (2025) - 3.
*Matsubara, T., Yaguchi, T.
"Number Theoretic Accelerated Learning of Physics-Informed Neural Networks"
Proc. of the 39th Annual AAAI Conference on Artificial Intelligence(AAAI2025), (2025) - 4.
*Matsubara, T., Yaguchi, T.
"Number Theoretic Accelerated Learning of Physics-Informed Neural Networks"
Proc. of The Eleventh International Conference on Learning Representations (ICLR2023), (2023) - 5.
*Chen, Y., Matsubara, T., Yaguchi, T.
"KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-Zero Training Loss"
Proc. of the 39th Annual AAAI Conference on Artificial Intelligence(AAAI2022), (2022) - 6.
*Chen, Y., Matsubara, T., Yaguchi, T.
"Neural Symplectic Form: Learning Hamiltonian Equations on General Coordinate Systems"
Advances in Neural Information Processing Systems (NeurIPS) 34, (2021) - 7.
*Matsubara, T., Miyatake,Y., Yaguchi, T.
"Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory"
Advances in Neural Information Processing Systems (NeurIPS) 34, (2021) - 8.
*Matsubara, T., Ishikawa, A., Yaguchi, T.
"Deep Energy-Based Modeling of Discrete-Time Physics"
Advances in Neural Information Processing Systems (NeurIPS) 33, pp. 13100-13111 (2020) - 9.
*Yaguchi, T.
"Lagrangian approach to deriving energy-preserving numerical schemes for the Euler–Lagrange partial differential equations"
M2AN 47, pp. 1493 – 1513 (2013) - 10.
*Yaguchi, T., Matsuo, T., Sugihara, M.
"The discrete variational derivative method based on discrete differential forms"
Journal of Computational Physics 231, pp. 3963-3986 (2012)
Lab Members
Principal investigator
- Takaharu Yaguchi
- Team Director
Contact Information
1-1 Rokkodai-cho, Nada-ku,
Kobe, Hyogo,
657-8501, Japan
Email: takaharu.yaguchi@riken.jp