Taken in Sumida, Tokyo.

My goal is to understand and develop a trustworthy and reliable machine learning system that collaborates with humans to provide useful technology and knowledge to society. Currently, I am a researcher at Preferred Networks, working on machine learning for healthcare and quantum chemistry domains.

Research interests: I am interested in machine learning algorithm analysis and design in general. More specifically, my current research topics include:

  • Loss function
  • Evaluation metric
  • Learning with reject option
  • Weakly supervised learning
  • Domain adaptation
  • Anomaly detection
  • Uncertainty quantification
  • Applications (e.g., speech signal processing, healthcare data analysis, molecular property prediction, neural network potentials, natural language processing)

I completed a PhD student under the supervision of Prof. Masashi Sugiyama in Sugiyama-Yokoya-Ishida laboratory, Department of computer science, The University of Tokyo. My doctoral thesis is “Theory and algorithms of machine learning with rejection based on loss function perspective”.

Links: Publications, CV