Operator Learning Based on Geometric Classical Field Theory and Infinite Dimensional Data Science
Operator Learning Based on Geometric Classical Field Theory and Infinite Dimensional Data Science

Collaborations

This project is related to the following projects:

JST CREST: Creating Information Utilization Platform by Integrating Mathematical and Information Sciences, and Development to Society "Structure Preserving System Modeling and Simulation Basis Based on Geometric Discrete Mechanics (2019–2024)

Research Director

  • Takaharu Yaguchi (Professor, Graduate School of Science, Kobe University / Team Director, RIKEN AIP)

Collaborator

  • Toshiaki Omori (Associate Professor, Graduate School of Engineering, Kobe University)
  • Nobutaka Takayama (Professor, Graduate School of Science, Kobe University)
  • Hiroaki Yoshimura (Professor, Faculty of Science and Engineering, Waseda University)

Project Overview

This project aimed to develop a discrete formulation of Lagrange–Dirac mechanics and to integrate it with various mathematical and information science techniques —such as symplectic geometry, automatic differentiation, computer algebra, sparse modeling, and neural differential equations— to build new theories and technologies for modeling and simulation. It was fundamental research on scientific machine learning methods that incorporate physical properties, and it laid the groundwork for the present project.

JST ASPIRE for the Next Generation "Deep scientific computing: integration of physical structure and deep learning through mathematical science

Research Director

  • Takaharu Yaguchi (Professor, Graduate School of Science, Kobe University / Team Director, RIKEN AIP)

Collaborator

  • Takashi Matsubara (Professor, Faculty of Information Science and Technology, Hokkaido University)
  • Masatoshi Imaizumi (Associate Professor, Graduate School of Arts and Sciences, the University of Tokyo / Team Director, RIKEN AIP)
  • Yusuke Tanaka (Research Scientist, NTT Communication Science Laboratories, NTT Corporation / Visiting Associate Professor, Graduate School of Science and Technology, NAIST)

International Collaborator (Principal Investigator)

  • Christopher J. Budd, OBE (University of Bath, United Kingdom)

Project Overview

This is an international research initiative on scientific machine learning in collaboration with the Maths4DL project, led by Prof. Budd at the University of Bath in the UK.
The ASPIRE program not only promotes cutting-edge research but also aims to foster globally competitive researchers by connecting young talents with world-class research groups. Within the framework of this project, collaborative research with international partners and initiatives such as the organization of the international conference SCML are being carried out to promote global research mobility and intellectual exchange.

Horizon Europe MSCA Staff Exchanges: REMODEL "Research Exchanges in the Mathematics of Deep Learning with Applications"

Partners

  • NTNU, Norway (coordinator)
  • Cambridge University, UK
  • Bath University, UK
  • TU Eindhoven, The Netherlands
  • Emory University, USA
  • Simon Fraser University, Canada
  • Kobe University, Japan

Project Overview

This project is an international collaborative research project on the mathematics of deep learning, led primarily by Professors Brynjulf Owren and Elena Celledoni at the Norwegian University of Science and Technology (NTNU).
In addition to our research group, it involves collaboration with research teams led by Prof. Owren at NTNU, Prof. Carola-Bibiane Schönlieb at Cambridge University, Prof. Christopher J. Budd at Bath University, Prof. Wil Schilders at TU Eindhoven, Prof. Lars Ruthotto at Emory University, and Prof. Ben Adcock at Simon Fraser University. Collaborative research is conducted through long-term mutual visits among these institutions. This project also works in close coordination with the JST ASPIRE program, jointly organizing numerous international workshops and symposia.