• PhD student in Dept. of Computer Science, The University of Tokyo

• Member of Issei Sato laboratory

• Research fellow at JSPS (DC1)

Google Scholar / Github / Twitter / CV

>> Japanese site

Others (invited talks / domestic conferences)

• Takeshi Koshizuka, Masahiro Fujisawa, Yusuke Tanaka and Issei Sato, "Why deep fourier neural operator performs worse: Revisiting the edge of chaos.", In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop (IBIS2023), Nov 2023.
  Received best student presentation award.

• Takeshi Koshizuka, "Diffusion generative model learning based on Schrödinger Bridge Problem" , A New Era in Mathematical Science: The Synergy of Numerical Analysis and Machine Learning, Nov 2023. (invited Talks)

• Takeshi Koshizuka and Issei Sato, "Neural Lagrangian Schrödinger Bridge for Population Dynamics", In Proceedings of Information-Based Induction Sciences and Machine Learning Workshop (IBIS2022), Nov 2022.
  Received outstanding student presentation award.

• Takeshi Koshizuka, Hidefumi Ohmura and Kouichi Katsurada, "A Vocoder-free Any-to-Many Voice Conversion using Pre-trained vq-wav2vec", IEICE Technical Report, SP2021-03, Vol. 120, No. 399, pp. 176--181, March 2021. [PDF]

• Yurie Hara, Naho Orita, Deng Ying, Takeshi Koshizuka and Sakai Hiromu, "Evidentiality, Modality and Causality--corpus and neurolinguistic studies.", IEICE Technical Report; IEICE Tech. Rep. 119.151 (2019): 15-15.

• Takeshi Koshizuka, Koh Takeuchi, Tatsushi Matsubayashi and Hiroshi Sawada, "Graph-based Regional NMF for Distributed Computing", DICOMO2019, pp. 743-751, 2019.
  Received best research paper award.

• D.Sc. in Comupter Science, The University of Tokyo, Apr. 2023 - Present

• M.Sc. in Computer Science, The University of Tokyo, Apr. 2021 - Mar. 2023

• B.Sc. in Information Science, Tokyo University of Science, Apr. 2017 - Mar. 2021