Taiji Suzuki
Taiji Suzuki (Ph.D.)
Title
Team Leader

Members

  • Team leader
    Taiji Suzuki
  • Research scientist
    Sho Sonoda
  • Postdoctoral researcher
    Kosaku Takanashi
  • Postdoctoral researcher
    Wei Huang
  • Visiting scientist
    Takafumi Kanamori
  • Visiting scientist
    Takashi Takenouchi
  • Visiting scientist
    Wataru Kumagai
  • Visiting scientist
    Atsushi Nitanda
  • Visiting scientist
    Hironori Fujisawa
  • Visiting scientist
    Shotaro Akaho
  • Visiting scientist
    Takayuki Kawashima
  • Visiting scientist
    Yuichiro Wada
  • Visiting scientist
    Kenta Oono
  • Visiting scientist
    Noboru Murata
  • Junior research associate
    Takumi Nakagawa

Introduction

Laboratory's photo

Our team, deep learning theory team, is studying various kinds of learning systems including deep learning from theoretical viewpoints. We enrich our understandings of complex learning systems, and leverage the insights to construct new machine learning techniques and apply them. Especially, machine learning should deal with high dimensional and complicated data, and thus we are studying deep learning and structured sparse learning as methods to deal with such complicated data. Moreover, we are also developing efficient optimization algorithms for large and complicated machine learning problems based on such techniques as stochastic optimization.

Main Research Field
Computer Science
Research Field
Mathematics
Research Subjects
Statistical learning theory of wide range of learning systems including deep learning
Efficient optimization algorithm for large dataset
High dimensional statistics
RIKEN Website URL

Introduction Video

Talk by Takuo Matsubara, Newcastle University/Alan Turing Institute<br> on Robust Generalised Bayesian Inference for Intractable Likelihoods thumbnails
Poster(s)

Related posts

posted on January 26, 2022 19:35Information
posted on October 8, 2021 16:33Information
posted on January 29, 2021 13:48Information
posted on January 26, 2021 15:17Information
posted on October 2, 2020 09:00Information
posted on March 13, 2020 11:20Information
posted on September 11, 2019 12:00Information
posted on September 7, 2018 17:55Information