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

1993 Fiscal Year Final Research Report Summary

SYMBIOSIS OF HETEROGENEOUS PARALLELISMS

Research Project

Project/Area Number 04650301
Research Category

Grant-in-Aid for General Scientific Research (C)

Allocation TypeSingle-year Grants
Research Field 情報工学
Research InstitutionIBARAKI UNIVERSITY

Principal Investigator

MATSUYAMA Yasuo  IBARAKI UNIVERSITY, DEPARTMENT OF COMPUTER AND INFORMATION SCIENCES PROFESSOR, 工学部, 教授 (60125804)

Project Period (FY) 1992 – 1993
KeywordsHeterogeneous parallelism / Connectionism / Massive parallelism / Learning / Multiple criteria optimization / log-bias / Mutation / Harmonic competition
Research Abstract

This study has a dual purpose : Designing an emulator which realizes symbiosis of heterogeneous parallelisms and presenting new connectionst learning algorithms. On the realization of the emulator, two workstations are used. One is for an SIMD mechanism where a finegrained parallelism is emulated. The other is for a coarse-grained parallelsm which controls the massive parallel part. KL1 was used for this control mechanism. The multiply descent cost competitive learning algorithm was run on this symbiotic system. The nondeterminism caused by the parallelsm was found to be rather meritorious for the exit from bad local minima.
For the developement of new learning algorithms, the head investigator presented two major new methods. On the supervised learning, the backpropagation with additional penalties was presented. This algorithm includes entropy/divergence penalties on the weithts and outputs. Pruning of the network and improvement of errors and generalization were acheived.
On the unsupervised case, the head investigator created the harmonic competitive learning. This algorithm enables to solve multiple criteria optimization with the aid of self-organization. The logarithmic competition bias and the logarithmic weight mutation solved the local optimality in the case of data compression.
Thus, this research project was completed by accomplishing the claimed results.

  • Research Products

    (12 results)

All Other

All Publications (12 results)

  • [Publications] Y.Matsuyama: "Learning in Competitive Networks with Penalties" Proc.Int.Joint Conf.on Neural Networks. IV. 773-778 (1992)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Matsuyama & M.Kobayashi: "Minimum Learning with Autonomous Cost Adjustment" Proc.Int.Joint Conf.on Neural Networks. II. 326-334 (1992)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Matsuyama & M.Kobayashi: "Fitting Competition" Proc.World Congress on Neural Networks. II. 567-574 (1993)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Matsuyama: "Competitive Learning among Massively Parallel Agents" Neural,Parallel & Scientific Computations. I. 181-198 (1993)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Matsuyama & M.Tan: "Multiply Desent Cost Competitive Learning as an Aid for Multimedia Image Processing" Proc.Int.Joint Conf.on Neural Networks. 3. 2061-2064 (1993)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Matsuyama & M.Tan: "Digital Movies Using Optimized Feature Maps" Proc.Int.Conf.on Neural Networks. x. y-z (1994)

    • Description
      「研究成果報告書概要(和文)」より
  • [Publications] Y.Matsuyama: "Laearning in Comptitive Networks with Penalties" Proc.Int.Joint Conf.on Neural Networks. vol.IV. 773-778 (1992)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Y.Matsuyama and M.kobayashi: "Minimum Learning with Autonomous Cost Adjustment" Proc.Int.Joint Conf.on Neural Networks. vol.II. 326-334 (1992)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Y.Matsuyama and Y.Kurosawa: "Coordination of Optimized Feature Map and Supervisory Concept" Proc.Int.Joint Conf.on Neural Networks. vol.II. 734-741 (1992)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Y.Matsuyama: "Competitive Learning among Massively Parallel Agents" Neural, Parallel & Scientific Computations. vol.1. 181-198 (1993)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Y.Matsuyama and M.Tan: "Multiply Descent Cost Competitive Learning as an Aid for Multimedia Image Proceasig" Proc.Int.Joint Conf.on Neural Networks. vol.3. 2061-2064 (1993)

    • Description
      「研究成果報告書概要(欧文)」より
  • [Publications] Y.Matsuyama and M.Tan: "Digital Movies Using Optimized feature Maps" Proc.Int.Conf.on Neural Networks. vol.x. y-z (1994)

    • Description
      「研究成果報告書概要(欧文)」より

URL: 

Published: 1995-03-27  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi