Presentation 2004/2/13
Pattern Recognition by Distributed Coding : Experiments and Considerations on the Power Space Similarity Method
Takao KOBAYASHI, Masaki NAKAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper considers pattern recognition methods by distributed coding. These methods can perform fast learning against a large amount of training samples and their recognition speed is fast and irrelevant to the size of the learning samples. This paper presents both of the basic algorithm and extend algorithms. Then, it describes experiments on real data by the power space similarity method which is a kind of distributed coding and considers the effectiveness.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Distributed Coding / Power Space Similarity method / Nearest Neighbor
Paper # TL2003-68,PRMU2003-254
Date of Issue

Conference Information
Committee TL
Conference Date 2004/2/13(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 Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Pattern Recognition by Distributed Coding : Experiments and Considerations on the Power Space Similarity Method
Sub Title (in English)
Keyword(1) Distributed Coding
Keyword(2) Power Space Similarity method
Keyword(3) Nearest Neighbor
1st Author's Name Takao KOBAYASHI
1st Author's Affiliation Faculty of Engineering, First University()
2nd Author's Name Masaki NAKAGAWA
2nd Author's Affiliation Faculty of Engineering, First University
Date 2004/2/13
Paper # TL2003-68,PRMU2003-254
Volume (vol) vol.103
Number (no) 657
Page pp.pp.-
#Pages 6
Date of Issue