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

Hardware Realization of Neural Oscillator with Learning Capability

Research Project

Project/Area Number 16500142
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeSingle-year Grants
Section一般
Research Field Sensitivity informatics/Soft computing
Research InstitutionKansai University

Principal Investigator

MAEDA Yutaka  Kansai University, Faculty of Engineering, Professor, 工学部, 教授 (60209393)

Project Period (FY) 2004 – 2005
Project Status Completed (Fiscal Year 2005)
Budget Amount *help
¥1,400,000 (Direct Cost: ¥1,400,000)
Fiscal Year 2005: ¥400,000 (Direct Cost: ¥400,000)
Fiscal Year 2004: ¥1,000,000 (Direct Cost: ¥1,000,000)
Keywordsneural oscillator / FPGA / learning / simultaneous perturbation / hardware implementation / FPAA / 同時摂動
Research Abstract

In this research, I propose a learning scheme for pulse coupled oscillators using the simultaneous perturbation optimization method and its hardware implementation. It was difficult and complicated for usual optimization method to find proper parameter values of the pulse coupled oscillator, since the oscillator is a kind of recurrent neural network. The simultaneous perturbation method gives a simple solution. Moreover, this approach is suitable for hardware realization. From this point of view, I proposed and fabricated the hardware pulse coupled oscillator and recurrent neural network with learning ability via the simultaneous perturbation method.
First of all, I confirm feasibility of the proposed pulse coupled oscillator with learning capability through simulation by C language and MatLab. The pulse coupled oscillator can generate pulse train with desired interval through leaning process.
Hardware realization of neural networks is an interesting issue. Mainly there are two approache … More s ; digital realization and analog one. As the former approach, field programmable gate array(FPGA) is useful target. I designed the pulse coupled oscillator with learning capability by VHDL. Then, design result is configured on FPGA. I verified the operation of the FPGA pulse coupled oscillator system with learning ability. Proper pulse train is obtained.
The second approach is analog realization. Then, field programmable analog array(FPAA) is adopted to implement the oscillator. Analog circuit design of the system is carried out. The circuit operation is confirmed by a circuit simulator. The system could realize the pulse coupled oscillator with learning capability via the simultaneous perturbation method. Next, the design is configured to FPAA. The circuit realized the pulse coupled oscillator. Interval of generated pulse train varied depending on parameters contained in the pulse coupled oscillator.
Moreover, some recurrent neural networks with learning capability were realized by FPGA using the simultaneous perturbation method. Hopfield network and bidirectional associative memory are typical examples of the recurrent networks. Usually, it was difficult to realize these hardware recurrent neural network systems with learning capability. However, I implemented the Hopfield neural network system and bidirectional neural network system with learning ability using the simultaneous perturbation method. I showed some application of these systems.
As a result, I could confirm a validity and feasibility of the pulse coupled oscillator with learning capability via the simultaneous perturbation method. These systems were fabricated and tested the operation of these systems. Less

Report

(3 results)
  • 2005 Annual Research Report   Final Research Report Summary
  • 2004 Annual Research Report
  • Research Products

    (10 results)

All 2005 2004

All Journal Article (10 results)

  • [Journal Article] FPGA Implementation of Pulse Coupled Oscillator2005

    • Author(s)
      Yutaka Maeda, Makito Nakatsuka
    • Journal Title

      Proceedings of the International Joint Conference on Neural Networks

      Pages: 633-638

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2005 Annual Research Report 2005 Final Research Report Summary
  • [Journal Article] Bidirectional Associative Memory with Learning Capability Using Simultaneous Perturbation2005

    • Author(s)
      Yutaka Maeda, Masatoshi Wakamura
    • Journal Title

      Neurocomputing Vol.69

      Pages: 182-197

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2005 Annual Research Report 2005 Final Research Report Summary
  • [Journal Article] Simultaneous Perturbation Learning Rule for Recurrent Neural Networks and Its FPGA Implementation2005

    • Author(s)
      Yutaka Maeda, Masatoshi Wakamura
    • Journal Title

      IEEE Transactions on NEURAL NETWORKS Vol.16・No.6

      Pages: 1664-1672

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2005 Final Research Report Summary
  • [Journal Article] Simultaneous Perturbation Learning Rule for Recurrent Neural Networks and Its FPGA Implementation2005

    • Author(s)
      Yutaka Maeda, Masatoshi Wakamura
    • Journal Title

      IEEE Transactions on NEURAL NETWORKS Vol.16, No.6

      Pages: 1664-1672

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2005 Final Research Report Summary
  • [Journal Article] Simultaneous Perturbation Learning Rule for Recurrent Neural Networks and Its FPGA Implementation2005

    • Author(s)
      Yutaka Maeda, Masatoshi Wakamura
    • Journal Title

      IEEE Transactions on NEUEAL NETWORKS Vol.16, No.6

      Pages: 1664-1672

    • Related Report
      2005 Annual Research Report
  • [Journal Article] Bidirectional Associative Memory with Learning Capability Using Simultaneous Perturbation2005

    • Author(s)
      Yutaka Maeda, Masatoshi Wakamura
    • Journal Title

      Neurocomputing (印刷中)

    • Related Report
      2004 Annual Research Report
  • [Journal Article] Simultaneous Perturbation Learning Rule for Recurrent Neural Networks and Its FPGA Implementation2005

    • Author(s)
      Yutaka Maeda, Masatoshi Wakamura
    • Journal Title

      IEEE Transactions on NEURAL NETWORKS (印刷中)

    • Related Report
      2004 Annual Research Report
  • [Journal Article] Learning Using Simulataneous Perturbation for Pulse Coupled Oscillators2004

    • Author(s)
      Yutaka Maeda, Makito Nakatsuka
    • Journal Title

      Proceedings of the 47th IEEE International Midwest Symposium on Circuits and Systems Vol.II

      Pages: 377-380

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2005 Final Research Report Summary
  • [Journal Article] Learning Using Simultaneous Perturbation for Pulse Coupled Oscillators2004

    • Author(s)
      Yutaka Maeda, Makito Nakatsuka
    • Journal Title

      Proceedings of the 47th IEEE International Midwest Symposium on Circuits and Systems Vol.II

      Pages: 377-380

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2005 Final Research Report Summary
  • [Journal Article] Learning Using Simultaneous Perturbation for Pulse Coupled Oscillators2004

    • Author(s)
      Yutaka Maeda, Makito Nakatsuka
    • Journal Title

      Proceedings of the 47th IEEE International Midwest Symposium on Circuits and Systems VOL.II

      Pages: 377-380

    • Related Report
      2004 Annual Research Report

URL: 

Published: 2004-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi