• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2017 Fiscal Year Final Research Report

Nonlinear sparse modeling for high dimensional data by kernel methods

Planned Research

  • PDF
Project AreaInitiative for High-Dimensional Data-Driven Science through Deepening of Sparse Modeling
Project/Area Number 25120011
Research Category

Grant-in-Aid for Scientific Research on Innovative Areas (Research in a proposed research area)

Allocation TypeSingle-year Grants
Review Section Complex systems
Research InstitutionNational Institute of Advanced Industrial Science and Technology

Principal Investigator

Akaho Shotaro  国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究グループ長 (40356340)

Co-Investigator(Kenkyū-buntansha) 麻生 英樹  国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 副研究センター長 (10344194)
日野 英逸  筑波大学, システム情報系, 准教授 (10580079)
末谷 大道  大分大学, 理工学部, 教授 (40507167)
Project Period (FY) 2013-06-28 – 2018-03-31
Keywords機械学習 / 多変量時系列 / 時空間モデル
Outline of Final Research Achievements

We developed a kernel-based method that extracts common features from multi-modal data based on mutual information. We also developed a transfer learning algorithm that is based on information geometrical e-mixture.
We developed a method to extract mutual relation among multivariate time series such as neuron networks and share-sales data. We applied spatio-temporal data analysis to slow slip event.
We succeeded to extract phase transition phenomena of associative memory neural network model in a data-driven manner.

Free Research Field

機械学習

URL: 

Published: 2019-03-29  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi