ReLU Chaotic Neuron Model for Deep Chaotic Neural Networks

DOI Web Site
  • TAMURA Hiroto
    東京大学大学院　工学系研究科
  • KOHNO Takashi
    東京大学生産技術研究所　情報・エレクトロニクス系部門
  • AIHARA Kazuyuki
    東京大学生産技術研究所　情報・エレクトロニクス系部門

Bibliographic Information

Other Title
  • 深層カオスニューラルネットワークのためのReLUカオスニューロンモデル

Search this article

Description

<p>A deep neural network (DNN) has been in the center of attention in the field of machine learning, and the chaotic neuron and chaotic neural network (ChNN) models have been in the spotlight in computational neuroscience and nonlinear science. However, there are no studies on deep ChNN. In order to fill this gap, we propose a ReLU (rectifier linear unit) chaotic neuron model, which is necessary for the application of the chaotic neuron model to DNN with ReLU activation. We also show that even a single ReLU chaotic neuron can generate dynamically changing outputs in spite of the simplicity of ReLU.</p>

Journal

  • SEISAN KENKYU

    SEISAN KENKYU 70 (3), 183-185, 2018-05-01

    Institute of Industrial Science The University of Tokyo

Details 詳細情報について

Report a problem

Back to top