Presentation 2002/6/18
Noise Supplement Learning for Associative Memories Composed of Multilayer Perceptrons and Sparsely Interconnected Neural Networks
Yusuke MAGORI, Takeshi KAMIO, Mititada MORISUE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, we have proposed associative memories composed of multilayer perceptrons (MLPs) and sparsely interconnected neural networks (SINNs), named MLP-SINN. Our proposed associative memories are suitable for hardware implementation and have better performance than both MLPs and SINNs. However, the capabilities of MLP and SINN are not effectively used in the conventional MLP-SINN, because they are synthesized independently. In this report, we propose the noise supplement learning for MLP-SINN associative memories to improve them.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Associateve Memories / Multilayer Perceptrons / Sparsely Interconnected Neural Networks / Noise Supplement Learning
Paper # NLP2002-21
Date of Issue

Conference Information
Committee NLP
Conference Date 2002/6/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Noise Supplement Learning for Associative Memories Composed of Multilayer Perceptrons and Sparsely Interconnected Neural Networks
Sub Title (in English)
Keyword(1) Associateve Memories
Keyword(2) Multilayer Perceptrons
Keyword(3) Sparsely Interconnected Neural Networks
Keyword(4) Noise Supplement Learning
1st Author's Name Yusuke MAGORI
1st Author's Affiliation Department of Information Machines and Interfaces, Faculty of Information Sciences, Hiroshima City University()
2nd Author's Name Takeshi KAMIO
2nd Author's Affiliation Department of Information Machines and Interfaces, Faculty of Information Sciences, Hiroshima City University
3rd Author's Name Mititada MORISUE
3rd Author's Affiliation Department of Information Machines and Interfaces, Faculty of Information Sciences, Hiroshima City University
Date 2002/6/18
Paper # NLP2002-21
Volume (vol) vol.102
Number (no) 142
Page pp.pp.-
#Pages 6
Date of Issue