Naoya Takeishi

Naoya Takeishi Collaborateur scientifique HES (postdoc)


Naoya Takeishi joined the DMML Group as a postdoctoral researcher in September 2020. He received the B.Eng., M.Eng., and PhD in Engineering at the Department of Aeronautics and Astronautics, the University of Tokyo, in 2013, 2015, and 2018, respectively. He worked as a postdoctoral researcher at RIKEN Center for Advanced Intelligence Project, Japan, from 2018 to 2020.


Naoya Takeishi currently studies on effective and efficient integration of domain knowledge into machine learning. He is interested in using various types of knowledge, such as theoretical understandings of physical systems (e.g., differential equations and simulators) and logical formula. He also has expertise in theory and methodology of data-driven analysis of nonlinear dynamical systems. Moreover, he is working in applied domains of fault detection and space robotics.



Falkiewicz, Maciej; Takeishi, Naoya; Shekhzadeh, Imahn; Wehenkel, Antoine; Delaunoy, Arnaud; Louppe, Gilles; Kalousis, Alexandros

Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability Unpublished


Abstract | Links | BibTeX


Takeishi, Naoya; Kalousis, Alexandros

Deep Grey-Box Modeling With Adaptive Data-Driven Models Toward Trustworthy Estimation of Theory-Driven Models Unpublished

2022, (arXiv:2210.13103).

Abstract | Links | BibTeX


Takeishi, Naoya; Kalousis, Alexandros

Variational Autoencoder with Differentiable Physics Engine for Human Gait Analysis and Synthesis Workshop

Deep Generative Models and Downstream Applications Workshop, 2021.

Abstract | Links | BibTeX

Takeishi, Naoya; Kalousis, Alexandros

Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling Inproceedings

Advances in Neural Information Processing Systems 34, 2021.

Abstract | Links | BibTeX

Please refer also to personal webpage.