Rchr
J-GLOBAL ID:200901057586746898   Update date: Nov. 16, 2024

Nitta Tohru

ニッタ トオル | Nitta Tohru
Affiliation and department:
Homepage URL  (2): https://www2.rikkyo.ac.jp/web/tnitta/https://www2.rikkyo.ac.jp/web/tnitta/index-eng.html
Research field  (1): Soft computing
Research keywords  (5): Neural Network ,  Clifford algebra ,  singular point ,  Quaternion ,  Complex number
Research theme for competitive and other funds  (2):
  • 2016 - 2021 ニューラルネットワークの特異点の解消
  • 2002 - 2004 組み合せ構造を持つ確率モデル構築のための学習理論
Papers (83):
  • S. Yamauch, T. Nitta, T. Ohnishi. Learning Characteristics of Reverse Quaternion Neural Network. arXiv Preprint arXiv: 2411.05816v1. 2024
  • Tohru Nitta. Proposal of fully augmented complex-valued neural networks. Nonlinear Theory and Its Applications, IEICE. 2023. 14. 2. 175-192
  • Tohru Nitta. Fully Augmented Complex-Valued Neural Networks. Proceedings of the 2022 International Symposium on Nonlinear Theory and its Applications (NOLTA2022). 2022. 248-251
  • Y. Okawa, S. Kanoga, T. Hoshino, T. Nitta. Sequential Learning on sEMGs in Short- and Long-term Situations via Self-Training Semi-Supervised Support Vector Machine. Proceedings of the 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC2022). 2022. 3232-3235
  • Tohru Nitta. Spurious Local Minima of Deep ReLU Neural Networks in the Neural Tangent Kernel Regime. arXiv Preprint. 2022. arXiv:1806.04884v3
more...
MISC (10):
  • NITTA Tohru. Sufficient conditions for neural networks not to have critical points based on the hierarchical structure. IEICE technical report. Neurocomputing. 2013. 112. 480. 7-12
  • NITTA Tohru. Widely Linear Estimation in the High-Dimensional Domain. 2012. 51. 4. 384-389
  • NITTA Tohru. What a Single Complex-valued Neuron Can Do. The Journal of the Institute of Electronics, Information and Communication Engineers. 2004. 87. 6. 450-453
  • NITTA Tohru. Complex-valued Neural Networks. The Journal of the Institute of Electronics,Information and Communication Engineers. 2000. 83. 8. 612-615
  • TANAKA Toshio, NISHIDA Kenji, INAYOSHI Hiroaki, NITTA Tohru. An Emotion-Memory Model using Neural Networks. IEICE technical report. Neurocomputing. 2000. 100. 96. 41-48
more...
Books (11):
  • Complex-Valued Neural Networks: Adcances and Applications in The IEEE Press Series on Computational Intelligence, ed. Akira Hirose
    Wiley-IEEE Press 2013
  • Efficiency and Scalability Methods for Computational Intellect, eds. Boris Igelnik and Jacek M. Zurada
    Pennsylvania, Information Science Reference, USA 2013
  • Computational Modeling and Simulation of Intellect: Current State and Future Perspectives, ed. Boris Igelnik
    Pennsylvania, Information Science Reference, USA 2011
  • Complex-Valued Neural Networks : Utilizing High-Dimensional Parameters
    Information Science Reference, Pennsylvania, USA 2009 ISBN:9781605662145
  • Advances in Imaging and Electron Physics, Vol.152, eds. Peter W. Hawkes
    Elsevier, Amsterdam, The Netherlands 2008
more...
Lectures and oral presentations  (2):
  • 高次元ニューラルネットワーク
    (東京女子大学学会 数学部会 2022)
  • 双対数を用いたニューラルネットワークとその学習特性
    (東北大学 電気通信研究所 共同プロジェクト研究会 「高次元・時空間ニューロダイナミクスとそれに基づくシステム構築への展開」 2022)
Education (2):
  • 1983 - 1985 University of Tsukuba
  • 1979 - 1983 University of Tsukuba First Cluster of Colleges,College of Natural Sciences
Professional career (1):
  • Ph. D. degree in engineering (University of Tsukuba)
Work history (8):
  • 2024/04 - 現在 Professor, Department of Information and Mathematical Sciences, Division of Mathematical Sciences, Tokyo Woman’s Christian University,
  • 2023/04 - 2024/03 Professor, Department of Mathematics, Division of Mathematical Sciences, Tokyo Woman’s Christian University,
  • 2020/04 - 2023/03 Rikkyo University
  • 2001/04 - 2021/03 National Institute of Advanced Industrial Science and Technology
  • 2006/04 - 2008/03 Osaka University
Show all
Committee career (1):
  • 2010/04 - 2014/03 Japanese Neural Network Society board member
Association Membership(s) (2):
電子情報通信学会 ,  日本神経回路学会
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page