Durability of Affordable Neural Networks against Damaging Neurons

• UWATE Yoko

  Department of Dept. of Electrical and Electronics Engineering, Tokushima University Institute of Neuroinfomatics, University/ETH Zurich

• NISHIO Yoshifumi

  Department of Dept. of Electrical and Electronics Engineering, Tokushima University

• STOOP Ruedi

  Institute of Neuroinfomatics, University/ETH Zurich

抄録

Durability describes the ability of a device to operate properly in imperfect conditions. We have recently proposed a novel neural network structure called an “Affordable Neural Network” (AfNN), in which affordable neurons of the hidden layer are considered as the elements responsible for the robustness property as is observed in human brain function. Whereas earlier we have shown that AfNNs can still generalize and learn, here we show that these networks are robust against damages occurring after the learning process has terminated. The results support the view that AfNNs embody the important feature of durability. In our contribution, we investigate the durability of the AfNN when some of the neurons in the hidden layer are damaged after the learning process.

収録刊行物

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E92-A (2), 585-593, 2009

  一般社団法人 電子情報通信学会

キーワード

• affordable neural networks
• durability
• back propagation learning

詳細情報

• CRID: 1390282681286577280
• NII論文ID: 10026855913
• NII書誌ID: AA10826239
• DOI: 10.1587/transfun.e92.a.585
• ISSN: 17451337
• ISSN: 09168508
• Web Site: http://www.jstage.jst.go.jp/article/transfun/E92.A/2/E92.A_2_585/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可