Presentation 1996/12/14
A Neural Network Model between the Area V1 and the Area IT
Satoru Kato, Susumu Horiguchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It has been well known that orientation-selective cells in the striate cortex are organized as the spatial structure in the area V1 of the visual cortex, and stimulus-selective cells in the area IT only respond to simple geometrical patterns. However, the neural network structure and its learning principle between the area V1 and the area IT have not been studied sufficiently. This paper considers a neural network model between the area V1 and the area IT as well as its learning principle. We propose a hierarchical neural network based on the Kohonen's self-organizing model. Experimental results show that the hierarchical neural network organize orientation-selective cells in the area V1 and stimulus-selective cells responding to simple geometrical patterns in the area IT.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Area V1 / Area IT / Kohonen self-organization / Hierarchical Neural Network mode
Paper # NC96-73
Date of Issue

Conference Information
Committee NC
Conference Date 1996/12/14(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) A Neural Network Model between the Area V1 and the Area IT
Sub Title (in English)
Keyword(1) Area V1
Keyword(2) Area IT
Keyword(3) Kohonen self-organization
Keyword(4) Hierarchical Neural Network mode
1st Author's Name Satoru Kato
1st Author's Affiliation Graduate School of Information Science Japan Advanced Institute of Science and Technology (JAIST)()
2nd Author's Name Susumu Horiguchi
2nd Author's Affiliation Graduate School of Information Science Japan Advanced Institute of Science and Technology (JAIST)
Date 1996/12/14
Paper # NC96-73
Volume (vol) vol.96
Number (no) 430
Page pp.pp.-
#Pages 8
Date of Issue