A Cascade System of Dynamic Binary Neural Networks and Learning of Periodic Orbit

• MORIYASU Jungo

  Hosei University

• SAITO Toshimichi

  Hosei University

抄録

This paper studies a cascade system of dynamic binary neural networks. The system is characterized by signum activation function, ternary connection parameters, and integer threshold parameters. As a fundamental learning problem, we consider storage and stabilization of one desired binary periodic orbit that corresponds to control signals of switching circuits. For the storage, we present a simple method based on the correlation learning. For the stabilization, we present a sparsification method based on the mutation operation in the genetic algorithm. Using the Gray-code-based return map, the storage and stability can be investigated. Performing numerical experiments, effectiveness of the learning method is confirmed.

収録刊行物

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E98.D (9), 1622-1629, 2015

  一般社団法人 電子情報通信学会

キーワード

• binary neural networks
• deep learning
• switching circuits

詳細情報

• CRID: 1390282679354984064
• NII論文ID: 130005096802
• DOI: 10.1587/transinf.2014opp0011
• ISSN: 17451361
• ISSN: 09168532
• Web Site: https://www.jstage.jst.go.jp/article/transinf/E98.D/9/E98.D_2014OPP0011/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可