[AIP AI4S Seminar Series] ‘Symplectic Approaches for Learning Hamiltonian Systems’ Talk by Takaharu Yaguchi (Kyushu University and RIKEN AIP)

AIP AI4S (AI for Science) Seminar Series
The AIP AI4S (AI for Science) Seminar Series is organized by the RIKEN Center for Advanced Intelligence Project (AIP).

This seminar series features invited researchers presenting recent advances, emerging methodologies, and interdisciplinary applications in AI for Science.
Through this series, we aim to promote cross-disciplinary discussion, foster collaboration, and strengthen the AI for Science research community.
Details of each seminar will be announced individually.

Date & Time: 2:00pm-3:00pm (JST), April 16, 2026
Venue: Zoom meeting
Speaker: Takaharu Yaguchi
Affiliation: Professor, University of Tokyo / Visiting Scientist, RIKEN AIP
Title: Symplectic Approaches for Learning Hamiltonian Systems
Abstract:
In recent years, machine learning methods for physical simulation and modeling have attracted significant attention. In this talk, I will focus specifically on methods for Hamiltonian systems. Hamiltonian systems admit a geometric property known as symplecticity. Since this property characterizes Hamiltonian systems, it is expected that preserving it will ensure the conservation of physical laws such as the energy conservation law. In this talk, I will explain machine learning methods that preserve such properties.