[Kenji Yamanishi] Discovering Deep Knowledge from Complex Data and Its Value Creation


Research Director

Kenji Yamanishi

Kenji Yamanishi

Graduate School of Information Science and Technology, the University of Tokyo
Professor


Outline

The Bigdata that we deal with today has becomes not only huge but also extremely complex. In order to utilize such complex data it is important to discover knowledge that exist in the latent space that is not obserbable but lies deeply behind the data. We call such knowledge the “deep knowledge. In this research project, we aim at developing novel mathematical methodologies for discovering deep knowledge from complex data and creating values from it. We are specifically concerned with deep knowledge discovery from a complex network in which a huge number of small data sets are connected together and each data is heterogeneous and dynamic. The main issues are how we can relate the data sets in the network to obtain a macroscopic view and how to detect intrinsic changes occurring in it. In order to address these issues we develop basic technologies of latent dynamics, relational data aggregation, temporal networks, sequential optimal decision making, data jackets, cognitive modeling, etc. We apply these technologies into real data in the areas of marketing, education, social networks, medical sciences, etc. to demonstrate the validity of our methodologies for deep knowledge discovery.

Quick Access

Program

  • CREST
  • PRESTO
  • ACT-I
  • ERATO
  • ACT-C
  • ACCEL
  • ALCA
  • RISTEX
  • AIP Network Lab
  • JST ProjectDB
  • Global Activities
  • Diversity
  • OSpolicy
  • Yuugu
  • Questions