Presentation 1994/6/28
Self-organization of visual,spatio-temporal receptive fields
Takashi Takahashi, Yuzo Hirai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A model of self-organizing visual,spatio-temporal receptive fields is proposed.It consists of a one-layer feed forward network with multiple input channels of different delays.Every weight of the network is modified by random,two-dimensional time series input signals according to Generalized Hebbian Algorithm proposed by Sanger.The network is trained with random Gaussian noise inputs with nonzero mean.It is shown by simulation studies that a variety of spatio-temporal receptive fields are acquired by this network. Some of them have similar properties to visual neurons found in mammalian retina,especially to X- and Y-type ganglion cells.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Self-organization / Hebbian learning / principal components analysis / spatio-temporal receptive fields
Paper # NC94-18
Date of Issue

Conference Information
Committee NC
Conference Date 1994/6/28(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) Self-organization of visual,spatio-temporal receptive fields
Sub Title (in English)
Keyword(1) Self-organization
Keyword(2) Hebbian learning
Keyword(3) principal components analysis
Keyword(4) spatio-temporal receptive fields
1st Author's Name Takashi Takahashi
1st Author's Affiliation Doctoral Programs in Engineering,University of Tsukuba()
2nd Author's Name Yuzo Hirai
2nd Author's Affiliation Institute of Information Sciences and Electronics,University of Tsukuba
Date 1994/6/28
Paper # NC94-18
Volume (vol) vol.94
Number (no) 129
Page pp.pp.-
#Pages 8
Date of Issue