A Topology Preserving Neural Network for Nonstationary Distributions

• NAKAJIMA Taira

  the Department of Computer and Mathematical Sciences, Graduate School of Information Sciences, Tohoku University

• TAKIZAWA Hiroyuki

  the Department of Computer and Mathematical Sciences, Graduate School of Information Sciences, Tohoku University

• KOBAYSHI Hiroaki

  the Department of Computer and Mathematical Sciences, Graduate School of Information Sciences, Tohoku University

• NAKAMURA Tadao

  the Department of Computer and Mathematical Sciences, Graduate School of Information Sciences, Tohoku University

抄録

We propose a learning algorithm for self-organizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the network using the proposed algorithm can rapidly adjust itself to represent the topology of nonstationary input distributions.

収録刊行物

• IEICE transactions on information and systems

  IEICE transactions on information and systems 82 (7), 1131-1135, 1999-07-25

  一般社団法人電子情報通信学会

キーワード

• competitive Hebbian learning rule
• law of the jungle mechanism
• neural networks
• nonstationary probability distribution
• self-organizing map

詳細情報

• CRID: 1574231877208915200
• NII論文ID: 110003210163
• NII書誌ID: AA10826272
• ISSN: 09168532
• 本文言語コード: en
• データソース種別:
  • CiNii Articles