Osaka University Machine Learning & Systems Laboratory (Kawahara Lab.)

On the back of the digital transformation (DX) of social infrastructure and the strong interest in SDGs, the knowledge and technologies cultivated so far in the field of information science are in the phase of accelerating expansion to various scientific fields, industries and society in recent years. In particular, machine learning has become widely recognized as one of the most important fundamental information fields, which supports AI technologies rapidly pervading society, and is playing a indispensable role for the further development of increasingly sophisticated and diversified information infrastructure. In this laboratory, we will carry out basic study on new principles, algorithms, and models of machine learning, and at the same time, implement machine learning as a system and apply it to various fields while incorporating next-generation computing technology and software engineering that have been rapidly developing in recent years. Through the development and practice of information technology for this purpose, we will work on research activities and human resource development that contribute to solving problems in the increasingly large-scale and complex society and scientific fields, as well as wide-ranging information science.

Visit [Research] for more information about researches conducted by this laboratory.
(Visit [HERE] for the information about Strucured Learning Team led by Prof. Kawahara in RIKEN AIP Center)

[Join Us!] We are recruiting students who are interested in machine learning and its related fields!


Recent News
  • Our paper titled "Estimating counterfactual treatment outcomes over time in complex multi-agent scenarios" has been accepted for publication in IEEE Transactions on Neural Networks and Learning Systems (2024.01.28).
  • Our paper titled "Manifold alteration between major depressive disorder and healthy control subjects using dynamic mode decomposition in resting-state fMRI data" has been accepted for publication in Frontiers in Psychiatry (2024.01.15).
  • Our paper titled "Adaptive action supervision in reinforcement learning from real-world multi-agent demonstrations" has been accepted for publication in Proceedings of the 17th Int'l Conf. On Agents and Artificial Intelligence (ICAART'24) (2023.12.08).
  • Our paper titled "Dynamic mode decomposition for Koopman spectral analysis of elementary cellular automata" has been accepted for publication in Chaos (2023.12.01).
  • Our paper titled "Decentralized Policy Learning with Partial Observation and Mechanical Constraints for Multi-person Modeling Learning Systems," has been accepted for publication in Neural Networks (2023.11.30).
  • Dr. Shunji Umetani (Guest Professor) and Dr. Xiaoyu Yang (Project Postdoctoral Researcher) joined the laboratory (2023.10.2).
  • Our paper titled "Many-body Approximation for Non-negative Tensors" has been accepted for publication in 36th Conf. on Neural Information Processing Systems (NeurIPS'23) (2023.9.22).
  • Our paper titled "A Characteristic Function for Shapley-Value-Based Attribution of Anomaly Scores" has been accepted for publication in Transactions on Machine Learning Research (2023.7.11).
  • Our paper titled "euMMD: Efficiently Computing the MMD Two-Sample Test Statistic for Univariate Data" has been accepted for publication in Statistics and Computing (2023.6.22).
  • One research student joined the laboratory (2023.6.19).
  • Our paper titled "Stable Invariant Models with Koopman Spectra" has been accepted for publication in Neural Networks (2023.5.20).
  • Two assistant administrative staffs and one research student joined the laboratory (2023.5.1).
  • Five under-graduate students joined the laboratory (2023.4.17).
  • Dr. Konishi (Project Assistant Professor) and five graduate students joined the laboratory (2023.4.3).
  • Our (preliminary) homepage has been opened (2023.1.13).

Announcements
Talks, Seminars, Workshops etc.

Others
Projects
Links