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

Construction of Quaternionic Qubit Neural Network and Its Application to Signal Processing

Research Project

Project/Area Number 19K12141
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 61040:Soft computing-related
Research InstitutionUniversity of Hyogo

Principal Investigator

Isokawa Teijiro  兵庫県立大学, 工学研究科, 准教授 (70336832)

Co-Investigator(Kenkyū-buntansha) 松井 伸之  兵庫県立大学, 工学研究科, 特任教授 (10173783)
Project Period (FY) 2019-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2021: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2020: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2019: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Keywords複素ニューラルネットワーク / 量子情報処理 / 四元数 / 量子ビット / 量子ビットニューロンモデル / ニューラルネットワーク / イジングモデル
Outline of Research at the Start

本研究は,量子情報処理に基づくニューラルネットワークモデルを構築し,その基本性能の解析と工学応用の展開を目的としたものである.
研究期間中においては,量子ビットニューロンモデルの拡張ならびに深層型ネットワークモデルの構築,相互結合型ネットワークに基づく連想記憶モデルならびにイジングモデルの構築,拡張量子ビットニューラルネットワークの信号処理への応用という計三つの課題を遂行してゆく.

Outline of Final Research Achievements

The purposes of this project are to construct neuron model and its feedforward network based on quantum information processing, to analyze the properties of the network, and to evaluate the effectiveness and performances of the neural network by using real-world signals, as compared to conventional (real-valued) neural network. The following outcomes have been achieved in this project: (1) A neuron model that incorporates quaternionic algebra into qubit neuron model with complex-valued representation, and its feedforward neural network, called Quaternionic Qubit Neural Network (QQNN), with an error-backpropagation algorithm as its learning method. (2) QQNNs have been evaluated through a prediction problem of three-dimensional outputs of Lorenz equations, and it is shown that QQNNs have superior performance in prediction accuracies than real-valued NNs.

Academic Significance and Societal Importance of the Research Achievements

従来のニューラルネットワークでは,ニューロンと呼ばれる基本素子により信号を処理するシステムである.画像情報などの多次元データを処理するためには数多くのニューロンが必要となり,様々な学習アルゴリズムが提案されてきた.本研究課題では,ニューロンの数ではなく各ニューロンが有する性能を向上させることによって多次元のデータを処理という大規模化の方法を検討したものである.本課題で構成したニューラルネットワークでは,多次元のデータを処理するために量子情報処理および四次元の数体系を導入することにより,従来の実数に基づくニューラルネットワークよりも効率的に信号が処理できることを示し得た.

Report

(4 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (9 results)

All 2021 2020 2019

All Journal Article (2 results) (of which Peer Reviewed: 2 results) Presentation (7 results) (of which Int'l Joint Research: 5 results)

  • [Journal Article] Gradient Descent Learning for Hyperbolic Hopfield Associative Memory2021

    • Author(s)
      M.Tsuji, T.Isokawa, M.Kobayashi, N.Matsui, and N.Kamiura
    • Journal Title

      Transactions of the Institute of Systems, Control and Information Engineers

      Volume: 34 Pages: 11-22

    • NAID

      130008025155

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] A Projection Rule for Complex‐Valued Associative Memory with Partial Connections2020

    • Author(s)
      M.Tsuji, T.Isokawa, M.Kobayashi, N.Matsui, and N.Kamiura
    • Journal Title

      IEEJ Transactions on Electrical and Electronic Engineering

      Volume: 15 Issue: 9 Pages: 1327-1336

    • DOI

      10.1002/tee.23200

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Presentation] Affine Control Systems under Equal Time and Analytic Feedback Laws Applied to Edge Quantum Computing2021

    • Author(s)
      T.Itami (N.Matsui, T.Isokawa, N.Kouda, and T.Hashimoto)
    • Organizer
      Proceedings of SICE Annual Conference
    • Related Report
      2021 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Time Series Prediction by Quaternionic Qubit Neural Network2020

    • Author(s)
      T.Teguri (T.Isokawa, N.Matsui, H.Nishimura, and N.Kamiura)
    • Organizer
      Proceedings of the 2020 International Conference on Neural Networks (IJCNN2020-WCCI2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Constructing Convolutional Neural Networks Based on Quaterion2020

    • Author(s)
      S.Hongo (T.Isokawa, N.Matsui, H.Nishimura, and N.Kamiura)
    • Organizer
      Proceedings of the 2020 International Conference on Neural Networks (IJCNN2020-WCCI2020)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Measuring Weighting Factor of Eigenstates in Quantum Superposition by Classical Mechanical 'quantum' Computer2020

    • Author(s)
      T.Itami (N.Matsui, and T.Isokawa)
    • Organizer
      Proceedings of SICE Annual Conference
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Quantum Computation by Classical Mechanical Apparatuses2020

    • Author(s)
      T.Itami (N.Matsui, T.Isokawa, N.Kouda, and T.Hashimoto)
    • Organizer
      Proceedings of 2020 4th Scientific School on Dynamics of Complex Networks and their Application in Intellectual Robotics (DCNAIR)
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] 四元数表現を持つ量子ビットニューラルネットワークの時系列予測への適用2019

    • Author(s)
      手操卓也
    • Organizer
      第16回コンピューテーショナル・インテリジェンス研究会
    • Related Report
      2019 Research-status Report
  • [Presentation] 四元数畳み込みニューラルネットワークの構築と性能評価2019

    • Author(s)
      本郷嵩人
    • Organizer
      第16回コンピューテーショナル・インテリジェンス研究会
    • Related Report
      2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2023-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi