Banner Banner

PhD Shinichi Nakajima

Icon

Technische Universität Berlin
Probabilistic Modeling and Inference

Marchstraße 23, 10587 Berlin
https://www.tu.berlin/en/ml

Shinichi Nakajima Bifold research group lead
© Nakajima

PhD Shinichi Nakajima

Research Group Lead

Dr. Shinichi Nakajima is a member of Machine Learning Group in Technische Universität Berlin. He received the master degree on physics in 1995 from Kobe university, and worked with Nikon Corporation until September 2014 on statistical analysis, image processing, and machine learning. He received the doctoral degree on computer science in 2006 from Tokyo Institute of Technology. His research interest is in theory and applications of machine learning, in particular, Bayesian inference, generative modeling, uncertainty estimation, explainable artificial intelligence, and their applications for computer vision, natural language processing, science and quantum computing. At the BIFOLD he leads the research group "Probabilistic Modeling and Inference".

 

 

Khaled Kahouli, Stefaan Simon Pierre Hessmann, Klaus-Robert Müller, Shinichi Nakajima, Stefan Gugler, Niklas Wolf Andreas Gebauer

Molecular relaxation by reverse diffusion with time step prediction

April 16, 2024
https://arxiv.org/abs/2404.10935

Dennis Grinwald, Philipp Wiesner, Shinichi Nakajima

Solution Simplex Clustering for Heterogeneous Federated Learning

March 05, 2024
https://arxiv.org/pdf/2403.03333.pdf

Kim Andrea Nicoli, Christopher Anders, Lena Funcke, Karl Jansen, Shinichi Nakajima

NeuLat: a toolbox for neural samplers in lattice field theories

December 27, 2023
https://inspirehep.net/literature/2752003

Kim A. Nicoli, Christopher J. Anders, Tobias Hartung, Karl Jansen, Pan Kessel, Shinichi Nakajima

Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories

December 08, 2023
https://doi.org/10.1103/PhysRevD.108.114501

Kirill Bykov, Laura Kopf, Shinichi Nakajima, Marius Kloft, Marina M.-C. Höhne

Labeling Neural Representations with Inverse Recognition

November 22, 2023
https://doi.org/10.48550/arXiv.2311.13594