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

2011 Fiscal Year Final Research Report

Construction of a routing optimization algorithm

Research Project

  • PDF
Project/Area Number 21700180
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeSingle-year Grants
Research Field Intelligent informatics
Research InstitutionSaga University (2010-2011)
National Institute of Information and Communications Technology (2009)

Principal Investigator

NAKAYAMA Koichi  佐賀大学, 工学系・研究科, 准教授 (50418498)

Project Period (FY) 2009 – 2011
Keywords学習と知識獲得
Research Abstract

A new optimization algorithm was proposed and the basic experiment was conducted. The result of research was summarized as four papers. We proposed the Emergent Learning Algorithm that is applied for Mutually Connected Neural Network(MCNN). The Emergent Learning Algorithm uses three types of evaluation value that are node evaluation, link evaluation and whole network evaluation. The experimental results show that the MCNN obtains optimal network structure by Emergent Learning Algorithm.

  • Research Products

    (4 results)

All 2011 2010 2009

All Presentation (4 results)

  • [Presentation] 創発的手法による自由結合ネットワークの学習2011

    • Author(s)
      ○橋本武法, 中山功一
    • Organizer
      電気学会研究会資料
    • Place of Presentation
      佐賀
    • Year and Date
      20110900
  • [Presentation] 自由結合ネットワークと創発的学習手法2011

    • Author(s)
      橋本武法, ○中山功一
    • Organizer
      第25回人工知能学会全国大会
    • Place of Presentation
      盛岡
    • Year and Date
      20110600
  • [Presentation] 重層性に着目した創発システムに向けて2010

    • Author(s)
      ○中山功一
    • Organizer
      第24回人工知能学会全国大会
    • Place of Presentation
      長崎
    • Year and Date
      20100600
  • [Presentation] 進化的ルーティング最適化手法に向けた協力の進化に関する考察2009

    • Author(s)
      ○中山功一, 安藤広志
    • Organizer
      第10回AI若手の集いMYCOM2009
    • Place of Presentation
      静岡
    • Year and Date
      20090600

URL: 

Published: 2013-07-31  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi