[Hiroshi Ishikawa] High-dimensional data analysis by mathematical model of recognition and higher-order/multi-layer random fields


Research Director

Hiroshi Ishikawa

Hiroshi Ishikawa

Department of Computer Science and Engineering, Waseda University
Professor


Outline

Human-level ability to recognize objects and environment is essential for autonomous robots operating in general circumstances. Yet the technology, expected to be in high demand in the future Japanese society with its scarcity of labor force, is far from being realized. In this research, we aim to build a mathematical model of recognition that consists of a top-down model that dictates the property of the phenomenon of recognition and a bottom-up model that interacts with the data directly, as well as validating the model by putting it to use in the analysis of high dimensional real data such as images.

Quick Access

Program

  • CREST
  • PRESTO
  • ACT-I
  • ERATO
  • ACT-X
  • ACCEL
  • ALCA
  • RISTEX
  • AIP Network Lab
  • Global Activities
  • Diversity
  • SDGs
  • OSpolicy
  • Yuugu
  • Questions