Presentation 2000/3/15
Discrete Recognition of Several Objects by Two-D Spreading Associative Neural Network
Hirokazu KANAYAMA, Kiyomi NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Paying attention to the spatial recognition system in the brain, a spreading associative neural network had been proposed that could simultaneously recognize the position and shape of an object when it moved in both one-D and two-D spaces. The spreading associative neural network not only recognized the position of an object irrespective of its shape, but also recognized its shape irrespective of its position in both the learned and unlearned positions. In the present study, we developed a two-D spreading associative neural network possessing two-D discrete recognition characteristics based on the spreading associative neural network possessing one-D discrete recognition characteristics. The discrete recognition of the position and shape was possible for the objects with more than 37 pixels interval, when the size of each object was 20 × 20 pixels and the size of input field was 120 × 120 pixels.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spatial Recognition / Discrete Recognition / Two-D Spreading / Selective Attention
Paper # NC99-171
Date of Issue

Conference Information
Committee NC
Conference Date 2000/3/15(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) Discrete Recognition of Several Objects by Two-D Spreading Associative Neural Network
Sub Title (in English)
Keyword(1) Spatial Recognition
Keyword(2) Discrete Recognition
Keyword(3) Two-D Spreading
Keyword(4) Selective Attention
1st Author's Name Hirokazu KANAYAMA
1st Author's Affiliation Department of Electronics and Informatics Toyama Prefectural University()
2nd Author's Name Kiyomi NAKAMURA
2nd Author's Affiliation Department of Electronics and Informatics Toyama Prefectural University
Date 2000/3/15
Paper # NC99-171
Volume (vol) vol.99
Number (no) 686
Page pp.pp.-
#Pages 7
Date of Issue