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

Towards an Algebra for Distributed Deep Neural Networks

Research Project

Project/Area Number 19K22865
Research Category

Grant-in-Aid for Challenging Research (Exploratory)

Allocation TypeMulti-year Fund
Review Section Medium-sized Section 61:Human informatics and related fields
Research InstitutionTokyo Institute of Technology

Principal Investigator

Inoue Nakamasa  東京工業大学, 情報理工学院, 准教授 (10733397)

Project Period (FY) 2019-06-28 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥6,500,000 (Direct Cost: ¥5,000,000、Indirect Cost: ¥1,500,000)
Fiscal Year 2021: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2020: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2019: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Keywords深層学習 / メタ学習 / 画像認識 / 分散学習 / 代数学
Outline of Research at the Start

本研究の目的は,深層学習で得られるモデル間の「演算」を可能とする体系の構築である.データベース構築に利用されている関係代数の演算をモデル空間に導入することで,大量の計算機で独立に学習されたモデルの事後的統合を可能とすることを目指す.これにより,現存の小・中規模計算資源を有効活用できる分散学習の方法論を開拓する.この研究は,人工知能を用いた画像・映像認識システムを高精度化することに役立つものであり,近未来社会での活用が期待される.

Outline of Final Research Achievements

Deep learning technology for understanding images and audio has become essential in an advanced information society. In this project, results were obtained regarding a mechanism in which multiple neural networks learn cooperatively or adversarially. The main achievements include a new regularization method for generative adversarial networks called Augmented Cyclic Consistency Regularization, an adversarial sample generation method using a second-order Quasi Newton method, and a step size regularization method. The effectiveness of these methods was demonstrated using real image and audio data, and the results were presented at international conferences.

Academic Significance and Societal Importance of the Research Achievements

本研究の成果は実社会で活用されている画像認識・画像変換、音声認識・音声話者照合システムの高度化に貢献するものである。また、学術的には新たな学習アルゴリズムが情報工学分野、特にパターン認識およびニューラルネットワークの深層学習に貢献するものである。

Report

(6 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (3 results)

All 2023 2021

All Journal Article (1 results) (of which Peer Reviewed: 1 results) Presentation (2 results) (of which Int'l Joint Research: 2 results)

  • [Journal Article] Step restriction for improving adversarial attacks2023

    • Author(s)
      Goto Keita、Otake Shinta、Kawakami Rei、Inoue Nakamasa
    • Journal Title

      Proc. IEEE International Conference on Acoustics, Speech and Signal Processing

      Volume: 5 Pages: 1-5

    • DOI

      10.1109/icassp49357.2023.10094644

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Presentation] Optimizing Speaker Embeddings using Meta-Training2021

    • Author(s)
      Nakamasa Inoue, Keita Goto
    • Organizer
      APSIPA
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] Quasi-Newton Adversarial Attacks on Speaker Verification Systems2021

    • Author(s)
      Keita Goto, Nakamasa Inoue
    • Organizer
      APSIPA
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2019-07-04   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi