About me

Keigo NISHIDA (西田 圭吾)

I am a postdoctoral researcher in the Laboratory for Computational Molecular Design at RIKEN BDR, and I also concurrently work in the Approximate Bayesian Inference Team at RIKEN AIP. In RIKEN, I am working on exploring new computers that efficiently process Bayesian neural netrworks and applying Bayesian deep learning to drug discovery. I am also a visiting researcher at the CiNet working on fluctuation-driven information processing.

Reserch Keywords : Bayesian Deep Learning, Variational Inference, Uncertainty, Domain Specific Architectures

Work Experience

• 2023.4 - Present, RIKEN Center for Biosystems Dynamics Research (BDR), Laboratory for Computational Molecular Design, Special Postdoctral Researcher
• 2023.4 - Present, RIKEN Center for Advanced Intelligence Project (AIP), Generic Technology Research Group, Approximate Bayesian Inference Team, Conc. Special Postdoctral Researcher
• 2023.4 - 2024.3, RIKEN Center for Biosystems Dynamics Research (BDR), Laboratory for Computational Molecular Design, Postdoctral Researcher
• 2023.4 - 2024.3, RIKEN Center for Advanced Intelligence Project (AIP), Generic Technology Research Group, Approximate Bayesian Inference Team, Conc. Postdoctral Researcher
• 2022.9 - Present, NICT Center for Information and Neural Networks (CiNet), Guest Researcher
• 2020.4 - 2023.3, RIKEN Center for Biosystems Dynamics Research (BDR), Laboratory for Computational Molecular Design, Research Associate
• 2019.4 - 2020.3, RIKEN Junior Research Associate
• 2018.7 - 2018.9, Preferred Networks, Inc., Internship
• 2016.4 - 2018.6, RIKEN Center for Biosystems Dynamics Research (BDR), Laboratory for Computational Molecular Design, Part-timer
• 2013.5 - 2016.3, RIKEN Quantitative Biology Center (QBiC), Laboratory for Single Cell Gene Dynamics, Part-timer

Education

• 2022.12 Ph.D., Graduate School of Frontier Biosciences, Osaka University
Advisor: Guest Prof. Makoto Taiji
Thesis: Stable Learning Algorithm of Bayesian Deep Neural Networks towards Low Power Dedicated Processor
• 2018.3 M.E. in Frontier Biosciences, Graduate School of Frontier Biosciences, Osaka University
Advisor: Guest Prof. Makoto Taiji
Thesis: Development of FPGA interface module in LSI dedicated hardware for molecular dynamics
• 2016.3 B.E. in Electronics, School of Engineering Science, Osaka University
Advisor: Prof. Akira Sakai
Thesis: Dislocation structure and valence state analysis of direct bonding SrTiO3 micro memristor devices

Grants

• April. 2024 - March. 2027, RIKEN, Special Postdoctoral Researchers Program
• April. 2019 - March. 2020, RIKEN, Junior Research Associate Program
• Jul. 2017 - Jun. 2022, Masason Foundation, Full Member
• April. 2016 - March. 2022, Program for Leading Graduate Schools of the Ministry of Education, Culture, Sports, Science and Technology, Japan (K03)

Publications

Journal (peer-reviewed)

1. Kazufumi Hosoda, Keigo Nishida, Shigeto Seno, Tomohiro Mashita, Hideki Kashioka, Izumi Ohzawa, in Front. Neurosci., A Single Fast Hebbian-like Process Enabling One-Shot Class Addition in Deep Neural Networks Without Backbone Modification, Apr. 17, 2024.
paper
2. Keigo Nishida, Makoto Taiji, AdamB: Decoupled Bayes by Backprop With Gaussian Scale Mixture Prior, in IEEE Access, vol. 10, pp. 92959-92970, 2022, doi: 10.1109/ACCESS.2022.3203484.
paper code

Proceedings (peer-reviewed)

1. Gentaro Morimoto, Yohei M. Koyama, Hao Zhang, Teruhisa S. Komatsu, Yousuke Ohno, Keigo Nishida, Itta Ohmura, Hiroshi Koyama, Makoto Taiji, Hardware acceleration of tensor-structured multilevel ewald summation method on MDGRAPE-4A, a special-purpose computer system for molecular dynamics simulations, in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1-15, 2021
paper

Presentations

Invited Talk

1. 西田 圭吾, AdamB: AdamWのベイズ拡張による安定したベイズ深層学習法 人工知能学会 第125回人工知能基本問題研究会(SIG-FPAI), 盛岡, 2022.8.29-30

Links

Google Scholar