Presentation 2004/1/19
On the information separation by the product model of SOM and neural gas : Separation of position and direction information from visual inputs (Neurocomputing)
Akira DATE, Koji KURATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The visual input to a robot in a room is a function of two factors, the position and direction of the robot. To separate these two factors of information in the observed images, we have developed a computational model based on two learning algorithms, the Kohonen's self-organizing map (SOM) and the neural gas (GAS). Our model, a product of these two models, is SOM-like in one dimension of the unit array and GAS-like in the other dimension. By putting these algorithms, we demonstrate, by computer simulation, that position and direction are extracted separately in different dimensions of the unit array.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Self-organizing Map / Neual Gas / Information Separation / Self-Localization / Mobile Robots
Paper # NC2003-115
Date of Issue

Conference Information
Committee NC
Conference Date 2004/1/19(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On the information separation by the product model of SOM and neural gas : Separation of position and direction information from visual inputs (Neurocomputing)
Sub Title (in English)
Keyword(1) Self-organizing Map
Keyword(2) Neual Gas
Keyword(3) Information Separation
Keyword(4) Self-Localization
Keyword(5) Mobile Robots
1st Author's Name Akira DATE
1st Author's Affiliation Communications Research Laboratory()
2nd Author's Name Koji KURATA
2nd Author's Affiliation Faculty of Engineering, Univeristy of the Ryukyus
Date 2004/1/19
Paper # NC2003-115
Volume (vol) vol.103
Number (no) 601
Page pp.pp.-
#Pages 6
Date of Issue