Presentation 2008-12-13
A bi-directional neural network model of 3-D mental rotation
Mitsuru ASHIZAWA, Toshio INUI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Here, a neural network model for mental rotation is proposed. In this model, it is assumed that a mental image is represented in egocentric coordinates and rotated by an internally generated motor signal. The results of the simulation show that, after learning, a simple stimulus image can be mentally rotated successfully in the network. In addition, neurons in the hidden layer shared some characteristics with CIP and AIP neurons observed in physiological experiments in monkeys.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) mental rotation / neural network model
Paper # TL2008-45
Date of Issue

Conference Information
Committee TL
Conference Date 2008/12/6(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) A bi-directional neural network model of 3-D mental rotation
Sub Title (in English)
Keyword(1) mental rotation
Keyword(2) neural network model
1st Author's Name Mitsuru ASHIZAWA
1st Author's Affiliation Graduate School of Informatics, Kyoto University()
2nd Author's Name Toshio INUI
2nd Author's Affiliation Graduate School of Informatics, Kyoto University
Date 2008-12-13
Paper # TL2008-45
Volume (vol) vol.108
Number (no) 353
Page pp.pp.-
#Pages 6
Date of Issue