Presentation 2001/1/26
Multi-layered neural networks to simulate the multidimensional psychological space of representing facial expressions
Daisuke TSUZUKI, Hiroshi YAMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Over the years a number of psychological research on the perception and recognition of facial expressions of emotion have suggested that facial expressions might be represented in the multidimensional space. The present study attempted to simulate such a psychological process, i.e.the multidimensional placement of facial expressions, by the neural networks. We made three and five layered feed-forward neural networks learn the physical parameters of the schematic facial expressions of emotion. As a result, we obtained the similar spatial structure of representing those expressions in the networks as observed in the psychological studies.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Facial recognition processing / Facial space / Schematic face / Multi-layered neural network
Paper # HCS2000-46
Date of Issue

Conference Information
Committee HCS
Conference Date 2001/1/26(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 Human Communication Science (HCS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Multi-layered neural networks to simulate the multidimensional psychological space of representing facial expressions
Sub Title (in English)
Keyword(1) Facial recognition processing
Keyword(2) Facial space
Keyword(3) Schematic face
Keyword(4) Multi-layered neural network
1st Author's Name Daisuke TSUZUKI
1st Author's Affiliation Graduate School of Literature and Social Sciences, Nihon University()
2nd Author's Name Hiroshi YAMADA
2nd Author's Affiliation Department of Psychology, College of Humanities and Sciences, Nihon University
Date 2001/1/26
Paper # HCS2000-46
Volume (vol) vol.100
Number (no) 612
Page pp.pp.-
#Pages 6
Date of Issue