Presentation 1994/10/20
A Derivation Method of Hypercolumn Model from Formal Pattern Description
Naoyuki Tsuruta, Akinori Nakamura, Rin-ichiro Taniguchi, Makoto Amamiya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper,a derivation method of Hypercolumn model from formal descriptions of pattern are proposed.Hypercolumn model is a hierarchical neural network for pattern recognition.It's structure of local feature analysis can be described using two types of production rule based on class-instance concept and whole-parts concept.And the whole structure of Hypercolumn model can be generated by mapping to the derivation tree of the rules.In this strategy,to generate the recursive structure for size invariant or location invariant pattern recognition models is very easy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Pattern Analysis / Hypercolumn Model / Neuro-Programming / Formal Language
Paper # NLC94-15,PRU94-40
Date of Issue

Conference Information
Committee NLC
Conference Date 1994/10/20(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Derivation Method of Hypercolumn Model from Formal Pattern Description
Sub Title (in English)
Keyword(1) Pattern Analysis
Keyword(2) Hypercolumn Model
Keyword(3) Neuro-Programming
Keyword(4) Formal Language
1st Author's Name Naoyuki Tsuruta
1st Author's Affiliation Department of Information Systems,Graduate School,Kyushu University()
2nd Author's Name Akinori Nakamura
2nd Author's Affiliation Department of Information Systems,Graduate School,Kyushu University
3rd Author's Name Rin-ichiro Taniguchi
3rd Author's Affiliation Department of Information Systems,Graduate School,Kyushu University
4th Author's Name Makoto Amamiya
4th Author's Affiliation Department of Information Systems,Graduate School,Kyushu University
Date 1994/10/20
Paper # NLC94-15,PRU94-40
Volume (vol) vol.94
Number (no) 291
Page pp.pp.-
#Pages 8
Date of Issue